From 0a57e347ebaaed24c531719e6c7d7dec04fec860 Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Wed, 1 Nov 2023 04:06:20 +1100 Subject: [PATCH 1/9] chore: add mik0w to CODEOWNERS --- .github/CODEOWNERS | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index 6214733..1357993 100644 --- a/.github/CODEOWNERS +++ b/.github/CODEOWNERS @@ -1,10 +1,10 @@ # Project Leads -* @shsingh @sagarbhure +* @shsingh @sagarbhure # Core Contributors -/docs/ @shsingh @sagarbhure +/docs/ @shsingh @sagarbhure # ML01 Lead @@ -34,8 +34,8 @@ # ML06 Lead -#/docs/ML06* -#/docs/cheatsheets/ML06* +/docs/ML06* @mik0w +/docs/cheatsheets/ML06* @mik0w @shsingh @sagarbhure # ML07 Lead From d09f4c79596f04067ce51527466146e9e6040a7a Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Wed, 1 Nov 2023 04:15:25 +1100 Subject: [PATCH 2/9] fix: test updating ML06 to verify CODEOWNERS working --- docs/ML06_2023-AI_Supply_Chain_Attacks.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/ML06_2023-AI_Supply_Chain_Attacks.md b/docs/ML06_2023-AI_Supply_Chain_Attacks.md index 07528a0..d11e79d 100644 --- a/docs/ML06_2023-AI_Supply_Chain_Attacks.md +++ b/docs/ML06_2023-AI_Supply_Chain_Attacks.md @@ -87,4 +87,4 @@ long time, since the victim may not realize that the package they are using has been compromised. The attacker's malicious code could be used to steal sensitive information, modify results, or even cause the machine learning model to fail. -## References +## References From 209b70b9778c3f250a54735cdd7bba990b865937 Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Wed, 1 Nov 2023 04:26:17 +1100 Subject: [PATCH 3/9] docs: add @adityoari as a contributor --- .all-contributorsrc | 10 ++++++++++ CONTRIBUTORS.md | 3 +++ README.md | 19 ++++++++++--------- 3 files changed, 23 insertions(+), 9 deletions(-) diff --git a/.all-contributorsrc b/.all-contributorsrc index 1d915d9..e84ffd0 100644 --- a/.all-contributorsrc +++ b/.all-contributorsrc @@ -111,6 +111,16 @@ "question", "promotion" ] + }, + { + "login": "adityoari", + "name": "Adit Nugroho", + "avatar_url": "https://avatars.githubusercontent.com/u/28642576?v=4", + "profile": "https://github.com/adityoari", + "contributions": [ + "code", + "doc" + ] } ], "contributorsPerLine": 9 diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.md index 21b803c..42e67d3 100644 --- a/CONTRIBUTORS.md +++ b/CONTRIBUTORS.md @@ -19,6 +19,9 @@ Thanks goes to these wonderful people Aryan Kenchappagol
Aryan Kenchappagol
📖 Mikołaj Kowalczyk
Mikołaj Kowalczyk
💻 📖 💬 📣 + + Adit Nugroho
Adit Nugroho
💻 📖 + diff --git a/README.md b/README.md index 768e122..ed9f0cb 100644 --- a/README.md +++ b/README.md @@ -47,17 +47,18 @@ Thanks goes to these wonderful people - - - - - - - + + + + + + + + + - - +
Sagar Bhure
Sagar Bhure
💻 📖 👀 💬 🖋 🔬 📣		Shain Singh
Shain Singh
💻 📖 👀 💬 🖋 📣 📆		Rob van der Veer
Rob van der Veer
👀 💻 📖 💬 📣		M S Nishanth
M S Nishanth
💻 💬		Rick M
Rick M
💻		Harold Blankenship
Harold Blankenship
💻		RiccardoBiosas
RiccardoBiosas
💻		Sagar Bhure
Sagar Bhure
💻 📖 👀 💬 🖋 🔬 📣		Shain Singh
Shain Singh
💻 📖 👀 💬 🖋 📣 📆		Rob van der Veer
Rob van der Veer
👀 💻 📖 💬 📣		M S Nishanth
M S Nishanth
💻 💬		Rick M
Rick M
💻		Harold Blankenship
Harold Blankenship
💻		RiccardoBiosas
RiccardoBiosas
💻		Aryan Kenchappagol
Aryan Kenchappagol
📖		Mikołaj Kowalczyk
Mikołaj Kowalczyk
💻 📖 💬 📣
Aryan Kenchappagol
Aryan Kenchappagol
📖		Mikołaj Kowalczyk
Mikołaj Kowalczyk
💻 📖 💬 📣		Adit Nugroho
Adit Nugroho
💻 📖
From aaabc6088a3e53f0147f7b53911dab19a63705fb Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Wed, 1 Nov 2023 04:28:02 +1100 Subject: [PATCH 4/9] docs: update @aryanxk02 as a contributor --- .all-contributorsrc | 5 ++++- CONTRIBUTORS.md | 2 +- README.md | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.all-contributorsrc b/.all-contributorsrc index e84ffd0..5592382 100644 --- a/.all-contributorsrc +++ b/.all-contributorsrc @@ -97,7 +97,10 @@ "avatar_url": "https://avatars.githubusercontent.com/u/59761275?v=4", "profile": "https://github.com/aryanxk02", "contributions": [ - "doc" + "doc", + "code", + "question", + "promotion" ] }, { diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.md index 42e67d3..37ce7ea 100644 --- a/CONTRIBUTORS.md +++ b/CONTRIBUTORS.md @@ -16,7 +16,7 @@ Thanks goes to these wonderful people Rick M
Rick M
💻 Harold Blankenship
Harold Blankenship
💻 RiccardoBiosas
RiccardoBiosas
💻 - Aryan Kenchappagol
Aryan Kenchappagol
📖 + Aryan Kenchappagol
Aryan Kenchappagol
📖 💻 💬 📣 Mikołaj Kowalczyk
Mikołaj Kowalczyk
💻 📖 💬 📣 diff --git a/README.md b/README.md index ed9f0cb..1a3c6d7 100644 --- a/README.md +++ b/README.md @@ -54,7 +54,7 @@ Thanks goes to these wonderful people Rick M
Rick M
💻 Harold Blankenship
Harold Blankenship
💻 RiccardoBiosas
RiccardoBiosas
💻 - Aryan Kenchappagol
Aryan Kenchappagol
📖 + Aryan Kenchappagol
Aryan Kenchappagol
📖 💻 💬 📣 Mikołaj Kowalczyk
Mikołaj Kowalczyk
💻 📖 💬 📣 From c117d639045524c2e51a0c310a4e6b32d4c9e15f Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Wed, 1 Nov 2023 04:32:07 +1100 Subject: [PATCH 5/9] chore: add adityoari to CONTRIBUTORS --- CONTRIBUTORS.md | 2 -- README.md | 2 -- 2 files changed, 4 deletions(-) diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.md index 37ce7ea..0afdf3a 100644 --- a/CONTRIBUTORS.md +++ b/CONTRIBUTORS.md @@ -18,8 +18,6 @@ Thanks goes to these wonderful people RiccardoBiosas
RiccardoBiosas
💻 Aryan Kenchappagol
Aryan Kenchappagol
📖 💻 💬 📣 Mikołaj Kowalczyk
Mikołaj Kowalczyk
💻 📖 💬 📣 - - Adit Nugroho
Adit Nugroho
💻 📖 diff --git a/README.md b/README.md index 1a3c6d7..6d6a8ae 100644 --- a/README.md +++ b/README.md @@ -56,8 +56,6 @@ Thanks goes to these wonderful people RiccardoBiosas
RiccardoBiosas
💻 Aryan Kenchappagol
Aryan Kenchappagol
📖 💻 💬 📣 Mikołaj Kowalczyk
Mikołaj Kowalczyk
💻 📖 💬 📣 - - Adit Nugroho
Adit Nugroho
💻 📖 From 25f0e4da2d2ae9990f170ba7a127f499150b13ff Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Wed, 1 Nov 2023 04:34:41 +1100 Subject: [PATCH 6/9] fix: README formatting --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 6d6a8ae..1a3c6d7 100644 --- a/README.md +++ b/README.md @@ -56,6 +56,8 @@ Thanks goes to these wonderful people RiccardoBiosas
RiccardoBiosas
💻 Aryan Kenchappagol
Aryan Kenchappagol
📖 💻 💬 📣 Mikołaj Kowalczyk
Mikołaj Kowalczyk
💻 📖 💬 📣 + + Adit Nugroho
Adit Nugroho
💻 📖 From 5797c2f910db1329e1da85f9cfa0963f1a0373b4 Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Thu, 2 Nov 2023 20:55:21 +1100 Subject: [PATCH 7/9] chore: add yodap-dg to CODEOWNERS --- .github/CODEOWNERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index 1357993..bbcd28f 100644 --- a/.github/CODEOWNERS +++ b/.github/CODEOWNERS @@ -19,8 +19,8 @@ # ML03 Lead -#/docs/ML03* -#/docs/cheatsheets/ML03* +/docs/ML03 @yodap-dg +/docs/cheatsheets/ML03* @yodap-dg @shsingh @sagarbhure # ML04 Lead From b79b07054f2c733bd222b0858bf9c8664309bd17 Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Wed, 15 Nov 2023 14:52:40 +1100 Subject: [PATCH 8/9] chore: archive gh issues --- github-open-issues-exported.md | 286 ++++++++++++++---- issues/2023-04-27.2.issue.open.md | 2 +- issues/2023-08-09.56.issue.closed.md | 6 +- ...open.md => 2023-10-20.128.issue.closed.md} | 6 +- issues/2023-10-20.129.pr.open.md | 40 ++- issues/2023-10-30.150.issue.open.md | 4 + issues/2023-10-30.154.issue.open.md | 4 + issues/2023-10-30.155.issue.open.md | 4 + issues/2023-10-30.163.issue.open.md | 2 +- issues/2023-10-30.164.issue.closed.md | 25 ++ issues/2023-10-30.164.issue.open.md | 19 -- issues/2023-10-30.165.issue.open.md | 2 +- issues/2023-10-30.166.issue.open.md | 2 +- issues/2023-10-30.167.issue.open.md | 2 +- issues/2023-10-30.168.issue.closed.md | 25 ++ issues/2023-10-30.168.issue.open.md | 19 -- issues/2023-10-30.169.issue.closed.md | 25 ++ issues/2023-10-30.169.issue.open.md | 19 -- issues/2023-10-30.170.issue.open.md | 2 +- issues/2023-10-30.171.issue.open.md | 2 +- issues/2023-10-30.172.issue.open.md | 2 +- issues/2023-10-30.175.pr.merged.md | 21 ++ issues/2023-10-30.176.pr.merged.md | 33 ++ issues/2023-10-30.177.pr.merged.md | 22 ++ issues/2023-10-31.178.issue.open.md | 19 ++ issues/2023-10-31.179.pr.merged.md | 14 + issues/2023-10-31.180.pr.merged.md | 21 ++ issues/2023-10-31.181.pr.merged.md | 19 ++ issues/2023-10-31.182.issue.open.md | 178 +++++++++++ issues/2023-11-02.183.pr.merged.md | 21 ++ issues/2023-11-15.184.pr.merged.md | 14 + issues/2023-11-15.185.pr.merged.md | 14 + 32 files changed, 747 insertions(+), 127 deletions(-) rename issues/{2023-10-20.128.issue.open.md => 2023-10-20.128.issue.closed.md} (72%) create mode 100644 issues/2023-10-30.164.issue.closed.md delete mode 100644 issues/2023-10-30.164.issue.open.md create mode 100644 issues/2023-10-30.168.issue.closed.md delete mode 100644 issues/2023-10-30.168.issue.open.md create mode 100644 issues/2023-10-30.169.issue.closed.md delete mode 100644 issues/2023-10-30.169.issue.open.md create mode 100644 issues/2023-10-30.175.pr.merged.md create mode 100644 issues/2023-10-30.176.pr.merged.md create mode 100644 issues/2023-10-30.177.pr.merged.md create mode 100644 issues/2023-10-31.178.issue.open.md create mode 100644 issues/2023-10-31.179.pr.merged.md create mode 100644 issues/2023-10-31.180.pr.merged.md create mode 100644 issues/2023-10-31.181.pr.merged.md create mode 100644 issues/2023-10-31.182.issue.open.md create mode 100644 issues/2023-11-02.183.pr.merged.md create mode 100644 issues/2023-11-15.184.pr.merged.md create mode 100644 issues/2023-11-15.185.pr.merged.md diff --git a/github-open-issues-exported.md b/github-open-issues-exported.md index d041e75..9e5a315 100644 --- a/github-open-issues-exported.md +++ b/github-open-issues-exported.md @@ -1,143 +1,286 @@ Export of Github issues for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10). -# [\#172 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/172) `open`: chore(admin): assign owner(s) for ML10 Model Poisoning -**Labels**: `help wanted`, `documentation/risks` +# [\#182 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/182) `open`: fix: merge review from @harrietf +**Labels**: `issues/triage`, `review needed` -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:31](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/172): +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-31 18:00](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/182): -- [ ] Assigned Lead Contributor for ML10 -- [ ] Update CODEOWNERS with contributor details +[Harriet Farlow](https://www.linkedin.com/in/harriet-farlow-654963b7/) sent through her feedback via mail. -Ideally the Lead Contributor for ML10 will also be assigned to the cheatsheet +Uploading Word doc and also outputting to Markdown in this issue to track. +Feedback in Word doc: [OWASP Top Ten Feedback.docx](https://github.com/OWASP/www-project-machine-learning-security-top-10/files/13219930/OWASP.Top.Ten.Feedback.docx) -------------------------------------------------------------------------------- +Output in Markdown from Word doc below: +--- +**General feedback - the list and the home page** + +I think this is great! Some feedback below: + +- I would also add something about these kinds of mitigations being + risk-based, and that each organisation should make a risk-based + assessment of which specific attacks are more likely to be employed + against their models, how impactful the ramifications would be (ie. + would they lose massive amounts of PII or would someone just get a + bad customer experience) and then decide on their ML security + posture from there. + +- I would also highlight some of the reasons why ML systems are + different to traditional cyber systems (ie. ML systems are + probabilistic while cyber systems are rules based, ML systems learn + and evolve while cyber systems are more static). From an + organisational perspective this means that it is unfair to expect + cyber security professionals to automatically know how best to + secure ML systems, and that there should be investment in training + and/or the creation of new roles + +- I would also add a comment about the terminology here being ML + security vs AI security. Clarify the difference between ML and AI + (ie. AI is a broader set of technologies while ML refers + specifically to the AI sub-field of ML models). For example, I + usually refer to my work as AI Security to be more encompassing of + an audience who is used to hearing about AI, but most of what I talk + about is actually ML security. Adding something here about these + terms would be useful for non-ML folk. + +**Some questions before I give feedback on these things** + +- Is the intention of the top 10 list that it is also ordered so that + #1 is most threatening, or is it unordered? + +- What is the methodology/reference for the risk factor values under + each threat? (I know it comes from the specific scenarios, but is it + meant to also be representative of 'common' ways of implementing the + attack? Because it could be very different and might be interpreted + as generic) + +**ML01:2023 Input Manipulation Attack** + +- Where Adversarial Attacks are referenced in the intro, I usually see + this referred to as an Adversarial Example instead and this language + would be more consistent. I'm also not sure what it means by saying + it's an umbrella term, what are the other attacks underneath this + umbrella? + +- The list Adversarial Training, Robust Models, Input Validation are + all good to include but could be rephrased to be mutually exclusive + (ie. the Robust Models section references both Adversarial Training + and Input Validation as the way to make models robust). You could + start with Robust Models first and still mention that those other + two techniques are some ways to make model robust, but is also + dependent on good data quality (clean data, good feature + engineering, complete data), model selection (having to choose an + appropriate balance between accuracy and interpretability, which are + usually trade-offs), considering ensemble methods instead of a + single model (ie. you get results from multiple models as a way of + checking and validation output). You can then into system level + security measures (input validation) and process-based security + measures (incorporating adversarial training). + +- Love the scenarios, that really helps to put it in perspective. + +**ML02:2023 Data Poisoning Attack** + +- Would be worth including more here in the 'about' section around how + this normally happens (an organisation's data repository could have + new data added, or existing data altered), why it works (an ML + model's heavy reliance on training data and the fact that it needs + LOTS of it, which means it's also very hard to spot if it has been + tampered with), who is likely to do this (someone either needs + access to the data repository if the model is trained on internal + data only in which case an insider threat scenario is more likely, + or if the model learns from 'new' data fed from the outside like a + chatbot that learns off inputs without validation (ie. Tay) then + this is a much easier attack) etc. Also clarify how this is + different to the cyber security challenge of just keeping data + secure (ie. it's more about the statistical distribution of the data + than the likelihood of data breach). + +- The 'how to prevent this section' is great, and adding more info + beforehand might help make it clearer as to why these measures are + important, and why the measure to secure data is for different + reasons than traditional cyber security threat models. + +- Again, great examples. You could add something like a chatbot or + social media model here to underscore how publicly injected data is + also a risk here. + +**ML03:2023 Model Inversion Attack & ML04:2023 Membership Inference +Attack** + +- These two attacks could be clarified as to exactly how they're + different, and depending on how you expect someone might use the Top + 10, you could consider combining them. For example, they both leak + information about data used to train the model but model inversion + is about leaking any data, and membership inference is more about + seeing if a specific piece of data was used. Or you could clarify + that they are separate based on the different controls used to + prevent it (ie. is the focus on differentiation here the goal of + attack, or the means of securing it) + +- Model inversion - you could explain what it means to + 'reverse-engineer' in this context. Ie. it is more about targeted + prompting than reverse engineering in a cyber context. This would + also explain why the suggested controls (ie. input verification) + work. + +**ML05:2023 Model Stealing** + +- This is good! Again, I think a longer description would be helpful. + +**ML06:2023 AI Supply Chain Attacks** + +- Yes, love that this is included! -# [\#171 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/171) `open`: chore(admin): assign owner(s) for ML09 Output Integrity Attack -**Labels**: `help wanted`, `documentation/risks` +- Why are we switching from ML to AI here? +**ML07:2023 Transfer Learning Attack** -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:30](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/171): +- This is interesting.. In my mind this is more an AI misuse issue + than an AI security issue, but it really depends on the scenario I + think. Could be worth clarifying here. -- [ ] Assigned Lead Contributor for ML09 -- [ ] Update CODEOWNERS with contributor details +**ML08:2023 Model Skewing** -Ideally the Lead Contributor for ML09 will also be assigned to the cheatsheet +- This also seems the same as the data poisoning attack.. It's not + clear how they're different. Usually when I saw model skewing the + attack is based on being able to change the model outcome without + actually touching the training data.. Would be worth clarifying + here. +**ML09:2023 Output Integrity Attack** +- Again, this attack overlaps a lot with other attacks already listed + that aim to impact the output, it's almost more of an umbrella term + in my mind. Or it could be different but it depends on how an + organisation creates its threat model. The controls mentioned here + are good though, so it's worth clarifying why this is listed as a + different attack and if it's based on the controls suggested (which + would also apply to the other attacks listed). +**ML10:2023 Model Poisoning** -------------------------------------------------------------------------------- +- Yes, this is good, and worth adding a bit more about how this can + happen (ie. direct alteration of the model through injection, the + interaction with hardware here and how this can be done in memory + etc) -# [\#170 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/170) `open`: chore(admin): assign owner(s) for ML08 Model Skewing -**Labels**: `help wanted`, `documentation/risks` -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:29](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/170): -- [ ] Assigned Lead Contributor for ML08 -- [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML08 will also be assigned to the cheatsheet +------------------------------------------------------------------------------- + +# [\#178 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/178) `open`: feat(docs): create a GLOSSARY page of commonly used terms +**Labels**: `documentation/general`, `help wanted` + + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-31 16:48](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/178): + +Machine Learning has a lot of terminology that may be new to people. Need to create a glossary page of commonly used terms. + +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 16:56](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/178#issuecomment-1787613865): +- [glossary page](https://github.com/OWASP/www-project-machine-learning-security-top-10/blob/master/tab_glossary.md) +- [rendered on site](https://owasp.org/www-project-machine-learning-security-top-10/#div-glossary) ------------------------------------------------------------------------------- -# [\#169 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/169) `open`: chore(admin): assign owner(s) for ML07 Transfer Learning Attack +# [\#172 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/172) `open`: chore(admin): assign owner(s) for ML10 Model Poisoning **Labels**: `help wanted`, `documentation/risks` -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:28](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/169): +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:31](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/172): -- [ ] Assigned Lead Contributor for ML07 +- [ ] Assigned Lead Contributor for ML10 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML07 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML10 will also be assigned to the cheatsheet - ref: #158 ------------------------------------------------------------------------------- -# [\#168 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/168) `open`: chore(admin): assign owner(s) for ML06 AI Supply Chain Attacks +# [\#171 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/171) `open`: chore(admin): assign owner(s) for ML09 Output Integrity Attack **Labels**: `help wanted`, `documentation/risks` -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:27](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/168): +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:30](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/171): -- [ ] Assigned Lead Contributor for ML06 +- [ ] Assigned Lead Contributor for ML09 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML06 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML09 will also be assigned to the cheatsheet - ref: #157 ------------------------------------------------------------------------------- -# [\#167 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/167) `open`: chore(admin): assign owner(s) for ML05 Model Stealing +# [\#170 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/170) `open`: chore(admin): assign owner(s) for ML08 Model Skewing **Labels**: `help wanted`, `documentation/risks` -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:27](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/167): +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:29](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/170): -- [ ] Assigned Lead Contributor for ML05 +- [ ] Assigned Lead Contributor for ML08 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML05 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML08 will also be assigned to the cheatsheet - ref: #156 ------------------------------------------------------------------------------- -# [\#166 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/166) `open`: chore(admin): assign owner(s) for ML04 Membership Inference Attack +# [\#167 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/167) `open`: chore(admin): assign owner(s) for ML05 Model Stealing **Labels**: `help wanted`, `documentation/risks` -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:26](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/166): +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:27](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/167): -- [ ] Assigned Lead Contributor for ML04 +- [ ] Assigned Lead Contributor for ML05 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML04 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML05 will also be assigned to the cheatsheet - ref: #153 ------------------------------------------------------------------------------- -# [\#165 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/165) `open`: chore(admin): assign owner(s) for ML03 Model Inversion Attack +# [\#166 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/166) `open`: chore(admin): assign owner(s) for ML04 Membership Inference Attack **Labels**: `help wanted`, `documentation/risks` -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:25](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/165): +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:26](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/166): -- [ ] Assigned Lead Contributor for ML03 +- [ ] Assigned Lead Contributor for ML04 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML03 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML04 will also be assigned to the cheatsheet - ref: #152 ------------------------------------------------------------------------------- -# [\#164 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/164) `open`: chore(admin): assign owner(s) for ML02 Data Poisoning Attack +# [\#165 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/165) `open`: chore(admin): assign owner(s) for ML03 Model Inversion Attack **Labels**: `help wanted`, `documentation/risks` -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:24](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/164): +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:25](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/165): -- [ ] Assigned Lead Contributor for ML02 +- [ ] Assigned Lead Contributor for ML03 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML02 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML03 will also be assigned to the cheatsheet - ref: #151 @@ -153,7 +296,7 @@ Ideally the Lead Contributor for ML02 will also be assigned to the cheatsheet - [ ] Assigned Lead Contributor for ML01 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML01 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML01 will also be assigned to the cheatsheet - ref: #147 @@ -235,7 +378,11 @@ Example Cheatsheet: [Input Validation Cheatsheet](https://github.com/OWASP/Cheat Example of Top 10 risk referencing cheatsheets: [ML01 Input Manipulation Attacks - Cheatsheets](https://github.com/OWASP/www-project-machine-learning-security-top-10/blob/master/docs/cheatsheets/ML01_2023-Input_Manipulation_Attack-Cheatsheet.md) +#### [shsingh](https://github.com/shsingh) commented at [2023-11-15 03:32](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/155#issuecomment-1811755511): + +adding @techiemac as potential lead to this due to his request for taking lead on the risk document. +adding @sagarbhure and @shsingh as backup ------------------------------------------------------------------------------- @@ -255,7 +402,11 @@ Example Cheatsheet: [Input Validation Cheatsheet](https://github.com/OWASP/Cheat Example of Top 10 risk referencing cheatsheets: [ML01 Input Manipulation Attacks - Cheatsheets](https://github.com/OWASP/www-project-machine-learning-security-top-10/blob/master/docs/cheatsheets/ML01_2023-Input_Manipulation_Attack-Cheatsheet.md) +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 17:01](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/154#issuecomment-1787621593): +adding @mik0w as potential lead to this due to his request for taking lead on the risk document. + +adding @sagarbhure and @shsingh as backup ------------------------------------------------------------------------------- @@ -335,7 +486,11 @@ Example Cheatsheet: [Input Validation Cheatsheet](https://github.com/OWASP/Cheat Example of Top 10 risk referencing cheatsheets: [ML01 Input Manipulation Attacks - Cheatsheets](https://github.com/OWASP/www-project-machine-learning-security-top-10/blob/master/docs/cheatsheets/ML01_2023-Input_Manipulation_Attack-Cheatsheet.md) +#### [shsingh](https://github.com/shsingh) commented at [2023-11-02 10:04](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/150#issuecomment-1790425001): + +adding @yodap-dg as potential lead to this due to his request for taking lead on the risk document. +adding @sagarbhure and @shsingh as backup ------------------------------------------------------------------------------- @@ -615,7 +770,7 @@ initial issue mentioned #43 ------------------------------------------------------------------------------- -# [\#129 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129) `open`: fix ePUB and WF to push updates to Repo +# [\#129 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129) `open`: fix ePUB Renders. #### [msnishanth9001](https://github.com/msnishanth9001) opened issue at [2023-10-20 06:50](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129): @@ -658,26 +813,43 @@ The intent is to do both fix mirror and formatting issues. Once the formatting i the following WF PR will publish ePUB and PDF. - https://github.com/mltop10-info/mltop10.info/pull/4 +#### [msnishanth9001](https://github.com/msnishanth9001) commented at [2023-10-30 07:30](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1784623302): -------------------------------------------------------------------------------- +updated PR to remove WF for mirror. + +This fixes ePUB and PDF render only. -# [\#128 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/128) `open`: Workflow to clone Top 10 attacks to mirror site https://mltop10.info/ -**Labels**: `documentation/general` +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 17:11](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1787638590): +Hi @msnishanth9001 as your change is only for the _quarto.yml file did you want to add that as a PR to the mltop10-info repo instead? -#### [msnishanth9001](https://github.com/msnishanth9001) opened issue at [2023-10-20 06:49](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/128): +The _quarto.yml file is not contained under docs/ in this project repository -Construct workflow to clone the Top 10 attack's MD File to the Repo https://github.com/mltop10-info/mltop10.info. +#### [msnishanth9001](https://github.com/msnishanth9001) commented at [2023-10-31 17:19](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1787651198): -So that all changes to attack scenarios are pushed by WF rather than human interaction. +was using it to test the renders, forgot to remove. Done now. -#### [shsingh](https://github.com/shsingh) commented at [2023-10-30 00:38](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/128#issuecomment-1784306108): +#### [shsingh](https://github.com/shsingh) commented at [2023-11-05 21:04](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1793845257): -Hi @msnishanth9001 +Hi @msnishanth9001, -commented on #129 +The files look like they have gone back to cfc455f7b7cb8cdac19e46d2321090e9085f619c -workflow for mirroring is at this stage less important then rendering of the markdown into pdf and epub. +Will they work properly on both the OWASP site as well as render PDF on https://mltop10.info site? + +#### [msnishanth9001](https://github.com/msnishanth9001) commented at [2023-11-06 14:54](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1795014821): + +> The files look like they have gone back to https://github.com/OWASP/www-project-machine-learning-security-top-10/commit/cfc455f7b7cb8cdac19e46d2321090e9085f619c + +- I have rebased the commit. + +> Will they work properly on both the OWASP site as well as render PDF on https://mltop10.info/ site? + +- yes. https://mltop10.info/ site needs this PR integrated. https://github.com/mltop10-info/mltop10.info/pull/6. +- ePUB file to verify ePUB render available on my fork. > https://github.com/msnishanth9001/mltop10.info/blob/epub-fixes/docs/OWASP-Machine-Learning-Security-Top-10.epub + +- for the fix to actually take effect you would have to run > quarto render and upload the new ePUB and PDF files. +- this WF is to make renders and upload new ePUB and PDF renders every time there is a change in MD files. https://github.com/mltop10-info/mltop10.info/pull/4 ------------------------------------------------------------------------------- @@ -859,7 +1031,7 @@ Each of the Top 10 items are scored according to [OWASP's Risk Rating Methodolog ------------------------------------------------------------------------------- # [\#2 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/2) `open`: fix: merge review from @robvanderveer -**Labels**: `issues/triage` +**Labels**: `issues/triage`, `review needed` #### [shsingh](https://github.com/shsingh) opened issue at [2023-04-27 10:07](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/2): diff --git a/issues/2023-04-27.2.issue.open.md b/issues/2023-04-27.2.issue.open.md index 2151567..bcd0e81 100644 --- a/issues/2023-04-27.2.issue.open.md +++ b/issues/2023-04-27.2.issue.open.md @@ -1,5 +1,5 @@ # [\#2 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/2) `open`: fix: merge review from @robvanderveer -**Labels**: `issues/triage` +**Labels**: `issues/triage`, `review needed` #### [shsingh](https://github.com/shsingh) opened issue at [2023-04-27 10:07](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/2): diff --git a/issues/2023-08-09.56.issue.closed.md b/issues/2023-08-09.56.issue.closed.md index 4dd9ca7..1204df4 100644 --- a/issues/2023-08-09.56.issue.closed.md +++ b/issues/2023-08-09.56.issue.closed.md @@ -2,7 +2,7 @@ **Labels**: `issues/general`, `documentation/general`, `good first issue`, `issues/triage` -#### [RAJANAGORI](https://github.com/RAJANAGORI) opened issue at [2023-08-09 12:52](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/56): +#### [RAJANAGORI](https://github.com/RAJANAGORI) opened issue at [2023-08-09 12:52](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/56): ### Type @@ -29,7 +29,7 @@ At the time of writing the top 10 the [OWASP Risk Methodology](https://owasp.org did you want to start working on #15 @RAJANAGORI ? -#### [RAJANAGORI](https://github.com/RAJANAGORI) commented at [2023-08-13 08:54](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/56#issuecomment-1676286436): +#### [RAJANAGORI](https://github.com/RAJANAGORI) commented at [2023-08-13 08:54](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/56#issuecomment-1676286436): @shsingh Sure, I will start working on this and raise the PR, but since I'm completely new to Machine learning concepts so I need to first understand the possible Likelihood and Impact based on the top 10 titles. @@ -42,7 +42,7 @@ Hi @RAJANAGORI , did you want me to create an example say for one of the ML risks to get you started? -#### [RAJANAGORI](https://github.com/RAJANAGORI) commented at [2023-08-16 11:14](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/56#issuecomment-1680412215): +#### [RAJANAGORI](https://github.com/RAJANAGORI) commented at [2023-08-16 11:14](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/56#issuecomment-1680412215): Sure, it would be a good idea. Since, you already know about the dots of every information. diff --git a/issues/2023-10-20.128.issue.open.md b/issues/2023-10-20.128.issue.closed.md similarity index 72% rename from issues/2023-10-20.128.issue.open.md rename to issues/2023-10-20.128.issue.closed.md index d0fe3b7..3d8aaae 100644 --- a/issues/2023-10-20.128.issue.open.md +++ b/issues/2023-10-20.128.issue.closed.md @@ -1,4 +1,4 @@ -# [\#128 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/128) `open`: Workflow to clone Top 10 attacks to mirror site https://mltop10.info/ +# [\#128 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/128) `closed`: Workflow to clone Top 10 attacks to mirror site https://mltop10.info/ **Labels**: `documentation/general` @@ -16,6 +16,10 @@ commented on #129 workflow for mirroring is at this stage less important then rendering of the markdown into pdf and epub. +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 17:52](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/128#issuecomment-1787706784): + +closing this issue for now. creating a workflow to mirror content will be done at later stage + ------------------------------------------------------------------------------- diff --git a/issues/2023-10-20.129.pr.open.md b/issues/2023-10-20.129.pr.open.md index d05468c..0db7ffe 100644 --- a/issues/2023-10-20.129.pr.open.md +++ b/issues/2023-10-20.129.pr.open.md @@ -1,4 +1,4 @@ -# [\#129 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129) `open`: fix ePUB and WF to push updates to Repo +# [\#129 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129) `open`: fix ePUB Renders. #### [msnishanth9001](https://github.com/msnishanth9001) opened issue at [2023-10-20 06:50](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129): @@ -41,6 +41,44 @@ The intent is to do both fix mirror and formatting issues. Once the formatting i the following WF PR will publish ePUB and PDF. - https://github.com/mltop10-info/mltop10.info/pull/4 +#### [msnishanth9001](https://github.com/msnishanth9001) commented at [2023-10-30 07:30](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1784623302): + +updated PR to remove WF for mirror. + +This fixes ePUB and PDF render only. + +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 17:11](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1787638590): + +Hi @msnishanth9001 as your change is only for the _quarto.yml file did you want to add that as a PR to the mltop10-info repo instead? + +The _quarto.yml file is not contained under docs/ in this project repository + +#### [msnishanth9001](https://github.com/msnishanth9001) commented at [2023-10-31 17:19](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1787651198): + +was using it to test the renders, forgot to remove. Done now. + +#### [shsingh](https://github.com/shsingh) commented at [2023-11-05 21:04](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1793845257): + +Hi @msnishanth9001, + +The files look like they have gone back to cfc455f7b7cb8cdac19e46d2321090e9085f619c + +Will they work properly on both the OWASP site as well as render PDF on https://mltop10.info site? + +#### [msnishanth9001](https://github.com/msnishanth9001) commented at [2023-11-06 14:54](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/129#issuecomment-1795014821): + +> The files look like they have gone back to https://github.com/OWASP/www-project-machine-learning-security-top-10/commit/cfc455f7b7cb8cdac19e46d2321090e9085f619c + +- I have rebased the commit. + +> Will they work properly on both the OWASP site as well as render PDF on https://mltop10.info/ site? + +- yes. https://mltop10.info/ site needs this PR integrated. https://github.com/mltop10-info/mltop10.info/pull/6. +- ePUB file to verify ePUB render available on my fork. > https://github.com/msnishanth9001/mltop10.info/blob/epub-fixes/docs/OWASP-Machine-Learning-Security-Top-10.epub + +- for the fix to actually take effect you would have to run > quarto render and upload the new ePUB and PDF files. +- this WF is to make renders and upload new ePUB and PDF renders every time there is a change in MD files. https://github.com/mltop10-info/mltop10.info/pull/4 + ------------------------------------------------------------------------------- diff --git a/issues/2023-10-30.150.issue.open.md b/issues/2023-10-30.150.issue.open.md index cc99d4f..f9cc3d2 100644 --- a/issues/2023-10-30.150.issue.open.md +++ b/issues/2023-10-30.150.issue.open.md @@ -13,7 +13,11 @@ Example Cheatsheet: [Input Validation Cheatsheet](https://github.com/OWASP/Cheat Example of Top 10 risk referencing cheatsheets: [ML01 Input Manipulation Attacks - Cheatsheets](https://github.com/OWASP/www-project-machine-learning-security-top-10/blob/master/docs/cheatsheets/ML01_2023-Input_Manipulation_Attack-Cheatsheet.md) +#### [shsingh](https://github.com/shsingh) commented at [2023-11-02 10:04](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/150#issuecomment-1790425001): +adding @yodap-dg as potential lead to this due to his request for taking lead on the risk document. + +adding @sagarbhure and @shsingh as backup ------------------------------------------------------------------------------- diff --git a/issues/2023-10-30.154.issue.open.md b/issues/2023-10-30.154.issue.open.md index 8ac1eb6..ab2817b 100644 --- a/issues/2023-10-30.154.issue.open.md +++ b/issues/2023-10-30.154.issue.open.md @@ -13,7 +13,11 @@ Example Cheatsheet: [Input Validation Cheatsheet](https://github.com/OWASP/Cheat Example of Top 10 risk referencing cheatsheets: [ML01 Input Manipulation Attacks - Cheatsheets](https://github.com/OWASP/www-project-machine-learning-security-top-10/blob/master/docs/cheatsheets/ML01_2023-Input_Manipulation_Attack-Cheatsheet.md) +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 17:01](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/154#issuecomment-1787621593): +adding @mik0w as potential lead to this due to his request for taking lead on the risk document. + +adding @sagarbhure and @shsingh as backup ------------------------------------------------------------------------------- diff --git a/issues/2023-10-30.155.issue.open.md b/issues/2023-10-30.155.issue.open.md index e508bc4..4598124 100644 --- a/issues/2023-10-30.155.issue.open.md +++ b/issues/2023-10-30.155.issue.open.md @@ -13,7 +13,11 @@ Example Cheatsheet: [Input Validation Cheatsheet](https://github.com/OWASP/Cheat Example of Top 10 risk referencing cheatsheets: [ML01 Input Manipulation Attacks - Cheatsheets](https://github.com/OWASP/www-project-machine-learning-security-top-10/blob/master/docs/cheatsheets/ML01_2023-Input_Manipulation_Attack-Cheatsheet.md) +#### [shsingh](https://github.com/shsingh) commented at [2023-11-15 03:32](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/155#issuecomment-1811755511): +adding @techiemac as potential lead to this due to his request for taking lead on the risk document. + +adding @sagarbhure and @shsingh as backup ------------------------------------------------------------------------------- diff --git a/issues/2023-10-30.163.issue.open.md b/issues/2023-10-30.163.issue.open.md index fd8ffe4..2cbff66 100644 --- a/issues/2023-10-30.163.issue.open.md +++ b/issues/2023-10-30.163.issue.open.md @@ -7,7 +7,7 @@ - [ ] Assigned Lead Contributor for ML01 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML01 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML01 will also be assigned to the cheatsheet - ref: #147 diff --git a/issues/2023-10-30.164.issue.closed.md b/issues/2023-10-30.164.issue.closed.md new file mode 100644 index 0000000..c5770b1 --- /dev/null +++ b/issues/2023-10-30.164.issue.closed.md @@ -0,0 +1,25 @@ +# [\#164 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/164) `closed`: chore(admin): assign owner(s) for ML02 Data Poisoning Attack +**Labels**: `help wanted`, `documentation/risks` + + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:24](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/164): + +- [x] Assigned Lead Contributor for ML02 +- [x] Update CODEOWNERS with contributor details + +Ideally the Lead Contributor for ML02 will also be assigned to the cheatsheet - ref: #150 + +#### [yodap-dg](https://github.com/yodap-dg) commented at [2023-11-01 19:52](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/164#issuecomment-1789578625): + +Hi @shsingh, I can take the lead on this one. Thanks. + +#### [shsingh](https://github.com/shsingh) commented at [2023-11-02 09:57](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/164#issuecomment-1790413458): + +ref: #183 + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-30.164.issue.open.md b/issues/2023-10-30.164.issue.open.md deleted file mode 100644 index 1049b12..0000000 --- a/issues/2023-10-30.164.issue.open.md +++ /dev/null @@ -1,19 +0,0 @@ -# [\#164 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/164) `open`: chore(admin): assign owner(s) for ML02 Data Poisoning Attack -**Labels**: `help wanted`, `documentation/risks` - - -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:24](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/164): - -- [ ] Assigned Lead Contributor for ML02 -- [ ] Update CODEOWNERS with contributor details - -Ideally the Lead Contributor for ML02 will also be assigned to the cheatsheet - - - - -------------------------------------------------------------------------------- - - - -[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-30.165.issue.open.md b/issues/2023-10-30.165.issue.open.md index a985acd..b46075a 100644 --- a/issues/2023-10-30.165.issue.open.md +++ b/issues/2023-10-30.165.issue.open.md @@ -7,7 +7,7 @@ - [ ] Assigned Lead Contributor for ML03 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML03 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML03 will also be assigned to the cheatsheet - ref: #151 diff --git a/issues/2023-10-30.166.issue.open.md b/issues/2023-10-30.166.issue.open.md index 1f023b3..4da6ef4 100644 --- a/issues/2023-10-30.166.issue.open.md +++ b/issues/2023-10-30.166.issue.open.md @@ -7,7 +7,7 @@ - [ ] Assigned Lead Contributor for ML04 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML04 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML04 will also be assigned to the cheatsheet - ref: #152 diff --git a/issues/2023-10-30.167.issue.open.md b/issues/2023-10-30.167.issue.open.md index 0c2af89..7de913e 100644 --- a/issues/2023-10-30.167.issue.open.md +++ b/issues/2023-10-30.167.issue.open.md @@ -7,7 +7,7 @@ - [ ] Assigned Lead Contributor for ML05 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML05 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML05 will also be assigned to the cheatsheet - ref: #153 diff --git a/issues/2023-10-30.168.issue.closed.md b/issues/2023-10-30.168.issue.closed.md new file mode 100644 index 0000000..837d3b9 --- /dev/null +++ b/issues/2023-10-30.168.issue.closed.md @@ -0,0 +1,25 @@ +# [\#168 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/168) `closed`: chore(admin): assign owner(s) for ML06 AI Supply Chain Attacks +**Labels**: `help wanted`, `documentation/risks` + + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:27](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/168): + +- [x] Assigned Lead Contributor for ML06 +- [x] Update CODEOWNERS with contributor details + +Ideally the Lead Contributor for ML06 will also be assigned to the cheatsheet - ref: #154 + +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 16:59](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/168#issuecomment-1787618233): + +@mik0w has indicated that he would like to lead the topic of "AI Supply Chain Attacks and Risks" + +#### [shsingh](https://github.com/shsingh) commented at [2023-11-02 09:59](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/168#issuecomment-1790415566): + +ref: #179 + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-30.168.issue.open.md b/issues/2023-10-30.168.issue.open.md deleted file mode 100644 index f19c7f2..0000000 --- a/issues/2023-10-30.168.issue.open.md +++ /dev/null @@ -1,19 +0,0 @@ -# [\#168 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/168) `open`: chore(admin): assign owner(s) for ML06 AI Supply Chain Attacks -**Labels**: `help wanted`, `documentation/risks` - - -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:27](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/168): - -- [ ] Assigned Lead Contributor for ML06 -- [ ] Update CODEOWNERS with contributor details - -Ideally the Lead Contributor for ML06 will also be assigned to the cheatsheet - - - - -------------------------------------------------------------------------------- - - - -[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-30.169.issue.closed.md b/issues/2023-10-30.169.issue.closed.md new file mode 100644 index 0000000..f32a644 --- /dev/null +++ b/issues/2023-10-30.169.issue.closed.md @@ -0,0 +1,25 @@ +# [\#169 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/169) `closed`: chore(admin): assign owner(s) for ML07 Transfer Learning Attack +**Labels**: `help wanted`, `documentation/risks` + + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:28](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/169): + +- [x] Assigned Lead Contributor for ML07 +- [x] Update CODEOWNERS with contributor details + +Ideally the Lead Contributor for ML07 will also be assigned to the cheatsheet - ref: #155 + +#### [techiemac](https://github.com/techiemac) commented at [2023-11-10 16:31](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/169#issuecomment-1806048695): + +Hey @shsingh I can take lead on this one + +#### [shsingh](https://github.com/shsingh) commented at [2023-11-15 03:30](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/169#issuecomment-1811753847): + +ref: #184 + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-30.169.issue.open.md b/issues/2023-10-30.169.issue.open.md deleted file mode 100644 index 6e5558b..0000000 --- a/issues/2023-10-30.169.issue.open.md +++ /dev/null @@ -1,19 +0,0 @@ -# [\#169 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/169) `open`: chore(admin): assign owner(s) for ML07 Transfer Learning Attack -**Labels**: `help wanted`, `documentation/risks` - - -#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 06:28](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/169): - -- [ ] Assigned Lead Contributor for ML07 -- [ ] Update CODEOWNERS with contributor details - -Ideally the Lead Contributor for ML07 will also be assigned to the cheatsheet - - - - -------------------------------------------------------------------------------- - - - -[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-30.170.issue.open.md b/issues/2023-10-30.170.issue.open.md index 3e25b49..558be4f 100644 --- a/issues/2023-10-30.170.issue.open.md +++ b/issues/2023-10-30.170.issue.open.md @@ -7,7 +7,7 @@ - [ ] Assigned Lead Contributor for ML08 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML08 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML08 will also be assigned to the cheatsheet - ref: #156 diff --git a/issues/2023-10-30.171.issue.open.md b/issues/2023-10-30.171.issue.open.md index 2fac9a1..2a5fc79 100644 --- a/issues/2023-10-30.171.issue.open.md +++ b/issues/2023-10-30.171.issue.open.md @@ -7,7 +7,7 @@ - [ ] Assigned Lead Contributor for ML09 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML09 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML09 will also be assigned to the cheatsheet - ref: #157 diff --git a/issues/2023-10-30.172.issue.open.md b/issues/2023-10-30.172.issue.open.md index 3af7c84..c0e4723 100644 --- a/issues/2023-10-30.172.issue.open.md +++ b/issues/2023-10-30.172.issue.open.md @@ -7,7 +7,7 @@ - [ ] Assigned Lead Contributor for ML10 - [ ] Update CODEOWNERS with contributor details -Ideally the Lead Contributor for ML10 will also be assigned to the cheatsheet +Ideally the Lead Contributor for ML10 will also be assigned to the cheatsheet - ref: #158 diff --git a/issues/2023-10-30.175.pr.merged.md b/issues/2023-10-30.175.pr.merged.md new file mode 100644 index 0000000..5148c47 --- /dev/null +++ b/issues/2023-10-30.175.pr.merged.md @@ -0,0 +1,21 @@ +# [\#175 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/175) `merged`: chore: archive gh issues + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 07:21](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/175): + +- feat: create example cheatsheet reference for ML01 +- fix: update cheatsheet for ML01 +- merge: develop (#160) +- chore: archive gh issues +- chore: archive gh issues +- chore: update CODEOWNERS +- chore: archive gh issues + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-30.176.pr.merged.md b/issues/2023-10-30.176.pr.merged.md new file mode 100644 index 0000000..c7656d8 --- /dev/null +++ b/issues/2023-10-30.176.pr.merged.md @@ -0,0 +1,33 @@ +# [\#176 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/176) `merged`: fix: add entries to GLOSSARY + +#### [adityoari](https://github.com/adityoari) opened issue at [2023-10-30 12:31](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/176): + +Add several entries into Glossary page: + +- Adversarial attack +- Classification +- Data labeling +- Data poisoning +- Ensemble +- IDS +- IPS +- MLOps +- Model +- Model ensemble +- Obfuscation +- Overfitting +- Regularisation +- Spam +- Underfitting + + +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 16:49](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/176#issuecomment-1787602563): + +ref: #178 + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-30.177.pr.merged.md b/issues/2023-10-30.177.pr.merged.md new file mode 100644 index 0000000..35bf22b --- /dev/null +++ b/issues/2023-10-30.177.pr.merged.md @@ -0,0 +1,22 @@ +# [\#177 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/177) `merged`: merge: develop + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-30 21:19](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/177): + +- feat: create example cheatsheet reference for ML01 +- fix: update cheatsheet for ML01 +- merge: develop (#160) +- chore: archive gh issues +- chore: archive gh issues +- chore: update CODEOWNERS +- chore: archive gh issues +- add entries to Glossary + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-31.178.issue.open.md b/issues/2023-10-31.178.issue.open.md new file mode 100644 index 0000000..107a446 --- /dev/null +++ b/issues/2023-10-31.178.issue.open.md @@ -0,0 +1,19 @@ +# [\#178 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/178) `open`: feat(docs): create a GLOSSARY page of commonly used terms +**Labels**: `documentation/general`, `help wanted` + + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-31 16:48](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/178): + +Machine Learning has a lot of terminology that may be new to people. Need to create a glossary page of commonly used terms. + +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 16:56](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/178#issuecomment-1787613865): + +- [glossary page](https://github.com/OWASP/www-project-machine-learning-security-top-10/blob/master/tab_glossary.md) +- [rendered on site](https://owasp.org/www-project-machine-learning-security-top-10/#div-glossary) + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-31.179.pr.merged.md b/issues/2023-10-31.179.pr.merged.md new file mode 100644 index 0000000..77f5b4d --- /dev/null +++ b/issues/2023-10-31.179.pr.merged.md @@ -0,0 +1,14 @@ +# [\#179 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/179) `merged`: chore: add mik0w to CODEOWNERS + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-31 17:06](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/179): + + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-31.180.pr.merged.md b/issues/2023-10-31.180.pr.merged.md new file mode 100644 index 0000000..0b424b4 --- /dev/null +++ b/issues/2023-10-31.180.pr.merged.md @@ -0,0 +1,21 @@ +# [\#180 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/180) `merged`: fix: test updating ML06 to verify CODEOWNERS working + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-31 17:16](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/180): + +- chore: add mik0w to CODEOWNERS +- fix: test updating ML06 to verify CODEOWNERS working + + +#### [shsingh](https://github.com/shsingh) commented at [2023-10-31 17:18](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/180#issuecomment-1787649598): + +Screenshot 2023-11-01 at 04 16 43 + +--- +@mik0w correctly shown as reviewer as per changes in #179 + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-31.181.pr.merged.md b/issues/2023-10-31.181.pr.merged.md new file mode 100644 index 0000000..09db3b1 --- /dev/null +++ b/issues/2023-10-31.181.pr.merged.md @@ -0,0 +1,19 @@ +# [\#181 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/181) `merged`: chore: update CONTRIBUTORS + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-31 17:32](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/181): + +- chore: add mik0w to CODEOWNERS +- fix: test updating ML06 to verify CODEOWNERS working +- docs: add @adityoari as a contributor +- docs: update @aryanxk02 as a contributor +- chore: add adityoari to CONTRIBUTORS + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-10-31.182.issue.open.md b/issues/2023-10-31.182.issue.open.md new file mode 100644 index 0000000..3fb1a26 --- /dev/null +++ b/issues/2023-10-31.182.issue.open.md @@ -0,0 +1,178 @@ +# [\#182 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/182) `open`: fix: merge review from @harrietf +**Labels**: `issues/triage`, `review needed` + + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-10-31 18:00](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/182): + +[Harriet Farlow](https://www.linkedin.com/in/harriet-farlow-654963b7/) sent through her feedback via mail. + +Uploading Word doc and also outputting to Markdown in this issue to track. + +Feedback in Word doc: [OWASP Top Ten Feedback.docx](https://github.com/OWASP/www-project-machine-learning-security-top-10/files/13219930/OWASP.Top.Ten.Feedback.docx) + + + +Output in Markdown from Word doc below: +--- +**General feedback - the list and the home page** + +I think this is great! Some feedback below: + +- I would also add something about these kinds of mitigations being + risk-based, and that each organisation should make a risk-based + assessment of which specific attacks are more likely to be employed + against their models, how impactful the ramifications would be (ie. + would they lose massive amounts of PII or would someone just get a + bad customer experience) and then decide on their ML security + posture from there. + +- I would also highlight some of the reasons why ML systems are + different to traditional cyber systems (ie. ML systems are + probabilistic while cyber systems are rules based, ML systems learn + and evolve while cyber systems are more static). From an + organisational perspective this means that it is unfair to expect + cyber security professionals to automatically know how best to + secure ML systems, and that there should be investment in training + and/or the creation of new roles + +- I would also add a comment about the terminology here being ML + security vs AI security. Clarify the difference between ML and AI + (ie. AI is a broader set of technologies while ML refers + specifically to the AI sub-field of ML models). For example, I + usually refer to my work as AI Security to be more encompassing of + an audience who is used to hearing about AI, but most of what I talk + about is actually ML security. Adding something here about these + terms would be useful for non-ML folk. + +**Some questions before I give feedback on these things** + +- Is the intention of the top 10 list that it is also ordered so that + #1 is most threatening, or is it unordered? + +- What is the methodology/reference for the risk factor values under + each threat? (I know it comes from the specific scenarios, but is it + meant to also be representative of 'common' ways of implementing the + attack? Because it could be very different and might be interpreted + as generic) + +**ML01:2023 Input Manipulation Attack** + +- Where Adversarial Attacks are referenced in the intro, I usually see + this referred to as an Adversarial Example instead and this language + would be more consistent. I'm also not sure what it means by saying + it's an umbrella term, what are the other attacks underneath this + umbrella? + +- The list Adversarial Training, Robust Models, Input Validation are + all good to include but could be rephrased to be mutually exclusive + (ie. the Robust Models section references both Adversarial Training + and Input Validation as the way to make models robust). You could + start with Robust Models first and still mention that those other + two techniques are some ways to make model robust, but is also + dependent on good data quality (clean data, good feature + engineering, complete data), model selection (having to choose an + appropriate balance between accuracy and interpretability, which are + usually trade-offs), considering ensemble methods instead of a + single model (ie. you get results from multiple models as a way of + checking and validation output). You can then into system level + security measures (input validation) and process-based security + measures (incorporating adversarial training). + +- Love the scenarios, that really helps to put it in perspective. + +**ML02:2023 Data Poisoning Attack** + +- Would be worth including more here in the 'about' section around how + this normally happens (an organisation's data repository could have + new data added, or existing data altered), why it works (an ML + model's heavy reliance on training data and the fact that it needs + LOTS of it, which means it's also very hard to spot if it has been + tampered with), who is likely to do this (someone either needs + access to the data repository if the model is trained on internal + data only in which case an insider threat scenario is more likely, + or if the model learns from 'new' data fed from the outside like a + chatbot that learns off inputs without validation (ie. Tay) then + this is a much easier attack) etc. Also clarify how this is + different to the cyber security challenge of just keeping data + secure (ie. it's more about the statistical distribution of the data + than the likelihood of data breach). + +- The 'how to prevent this section' is great, and adding more info + beforehand might help make it clearer as to why these measures are + important, and why the measure to secure data is for different + reasons than traditional cyber security threat models. + +- Again, great examples. You could add something like a chatbot or + social media model here to underscore how publicly injected data is + also a risk here. + +**ML03:2023 Model Inversion Attack & ML04:2023 Membership Inference +Attack** + +- These two attacks could be clarified as to exactly how they're + different, and depending on how you expect someone might use the Top + 10, you could consider combining them. For example, they both leak + information about data used to train the model but model inversion + is about leaking any data, and membership inference is more about + seeing if a specific piece of data was used. Or you could clarify + that they are separate based on the different controls used to + prevent it (ie. is the focus on differentiation here the goal of + attack, or the means of securing it) + +- Model inversion - you could explain what it means to + 'reverse-engineer' in this context. Ie. it is more about targeted + prompting than reverse engineering in a cyber context. This would + also explain why the suggested controls (ie. input verification) + work. + +**ML05:2023 Model Stealing** + +- This is good! Again, I think a longer description would be helpful. + +**ML06:2023 AI Supply Chain Attacks** + +- Yes, love that this is included! + +- Why are we switching from ML to AI here? + +**ML07:2023 Transfer Learning Attack** + +- This is interesting.. In my mind this is more an AI misuse issue + than an AI security issue, but it really depends on the scenario I + think. Could be worth clarifying here. + +**ML08:2023 Model Skewing** + +- This also seems the same as the data poisoning attack.. It's not + clear how they're different. Usually when I saw model skewing the + attack is based on being able to change the model outcome without + actually touching the training data.. Would be worth clarifying + here. + +**ML09:2023 Output Integrity Attack** + +- Again, this attack overlaps a lot with other attacks already listed + that aim to impact the output, it's almost more of an umbrella term + in my mind. Or it could be different but it depends on how an + organisation creates its threat model. The controls mentioned here + are good though, so it's worth clarifying why this is listed as a + different attack and if it's based on the controls suggested (which + would also apply to the other attacks listed). + +**ML10:2023 Model Poisoning** + +- Yes, this is good, and worth adding a bit more about how this can + happen (ie. direct alteration of the model through injection, the + interaction with hardware here and how this can be done in memory + etc) + + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-11-02.183.pr.merged.md b/issues/2023-11-02.183.pr.merged.md new file mode 100644 index 0000000..613031c --- /dev/null +++ b/issues/2023-11-02.183.pr.merged.md @@ -0,0 +1,21 @@ +# [\#183 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/183) `merged`: chore: add yodap-dg to CODEOWNERS + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-11-02 09:56](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/183): + +- chore: add mik0w to CODEOWNERS +- fix: test updating ML06 to verify CODEOWNERS working +- docs: add @adityoari as a contributor +- docs: update @aryanxk02 as a contributor +- chore: add adityoari to CONTRIBUTORS +- fix: README formatting +- chore: add yodap-dg to CODEOWNERS + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-11-15.184.pr.merged.md b/issues/2023-11-15.184.pr.merged.md new file mode 100644 index 0000000..aeab7f4 --- /dev/null +++ b/issues/2023-11-15.184.pr.merged.md @@ -0,0 +1,14 @@ +# [\#184 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/184) `merged`: chore: add techiemac to CODEOWNERS + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-11-15 03:27](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/184): + + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-11-15.185.pr.merged.md b/issues/2023-11-15.185.pr.merged.md new file mode 100644 index 0000000..6d3816a --- /dev/null +++ b/issues/2023-11-15.185.pr.merged.md @@ -0,0 +1,14 @@ +# [\#185 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/185) `merged`: merge develop + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-11-15 03:44](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/185): + + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] From d11deaf378cae28e7824e43e3cbb8adb9947c88a Mon Sep 17 00:00:00 2001 From: Shain Singh Date: Tue, 28 Nov 2023 12:44:46 +1100 Subject: [PATCH 9/9] chore: github issues archive --- github-open-issues-exported.md | 82 +++++++++++++++++++++++++++++ issues/2023-11-15.186.pr.merged.md | 22 ++++++++ issues/2023-11-16.187.issue.open.md | 31 +++++++++++ issues/2023-11-17.188.issue.open.md | 30 +++++++++++ issues/2023-11-23.189.issue.open.md | 30 +++++++++++ 5 files changed, 195 insertions(+) create mode 100644 issues/2023-11-15.186.pr.merged.md create mode 100644 issues/2023-11-16.187.issue.open.md create mode 100644 issues/2023-11-17.188.issue.open.md create mode 100644 issues/2023-11-23.189.issue.open.md diff --git a/github-open-issues-exported.md b/github-open-issues-exported.md index 9e5a315..0c16d2b 100644 --- a/github-open-issues-exported.md +++ b/github-open-issues-exported.md @@ -1,5 +1,87 @@ Export of Github issues for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10). +# [\#189 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/189) `open`: [FEEDBACK]: Include a page with a brief descriptions of each of the vulnerabilities +**Labels**: `issues/general`, `issues/triage` + + +#### [mik0w](https://github.com/mik0w) opened issue at [2023-11-23 12:08](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/189): + +### Type + +Suggestions for Improvement + +### What would you like to report? + +For example in Top10 for LLM there's this page with a summary of each of the vulnerabilities, which I think would be pretty useful to have in Top10 for ML as well. + +Sometimes when you e.g. work on some slides for a presentation, you just want to get a short summary of each of the vulnerabilities. In my opinion including such a page in Top10 for ML would be an improvement: + +![summary](https://github.com/OWASP/www-project-machine-learning-security-top-10/assets/64902909/0bc2b1c8-43a0-4a5d-b549-71cf83e897c1) + +### Code of Conduct + +- [X] I agree to follow this project's Code of Conduct + + + + +------------------------------------------------------------------------------- + +# [\#188 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/188) `open`: [FEEDBACK]: Include MLOps vulnerabilties somewhere in the Supply Chain Security category +**Labels**: `issues/general`, `issues/triage` + + +#### [mik0w](https://github.com/mik0w) opened issue at [2023-11-17 10:26](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/188): + +### Type + +Suggestions for Improvement + +### What would you like to report? + +**Context** +One of the parts of the supply chain in modern ML systems is MLOps software - like i.e. MLFlow, Prefect etc. Those systems are vulnerable to classic web based attacks and they seem to be "misconfured by default". I've described it here: https://hackstery.com/2023/10/13/no-one-is-prefect-is-your-mlops-infrastructure-leaking-secrets/ or here: https://github.com/logspace-ai/langflow/issues/1145 + +**Suggestion for improvement** +I'd suggest including MLOps-related vulnerabilities in the ML06 (or maybe in some other categories as well? I am open for suggestions). + +### Code of Conduct + +- [X] I agree to follow this project's Code of Conduct + + + + +------------------------------------------------------------------------------- + +# [\#187 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/187) `open`: [FEEDBACK]: Sync attack names between LLMT10 and MLT10 where appropriate +**Labels**: `issues/general`, `issues/triage` + + +#### [kapsolas](https://github.com/kapsolas) opened issue at [2023-11-16 22:16](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/187): + +### Type + +Suggestions for Improvement + +### What would you like to report? + +I would like to make the suggestion that we consolidate the terms used in the LLM and ML top 10 documents. + +Many of the top 10 items in each are closely related or even the same. +Where possible, the same term should be used (i.e. Model Theft vs Model Stealing, Data Poisoning Attack vs Training data Poisoning). + +Thanks! + +### Code of Conduct + +- [X] I agree to follow this project's Code of Conduct + + + + +------------------------------------------------------------------------------- + # [\#182 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/182) `open`: fix: merge review from @harrietf **Labels**: `issues/triage`, `review needed` diff --git a/issues/2023-11-15.186.pr.merged.md b/issues/2023-11-15.186.pr.merged.md new file mode 100644 index 0000000..9629b98 --- /dev/null +++ b/issues/2023-11-15.186.pr.merged.md @@ -0,0 +1,22 @@ +# [\#186 PR](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/186) `merged`: chore: archive github issues + +#### [shsingh](https://github.com/shsingh) opened issue at [2023-11-15 03:53](https://github.com/OWASP/www-project-machine-learning-security-top-10/pull/186): + +- chore: add mik0w to CODEOWNERS +- fix: test updating ML06 to verify CODEOWNERS working +- docs: add @adityoari as a contributor +- docs: update @aryanxk02 as a contributor +- chore: add adityoari to CONTRIBUTORS +- fix: README formatting +- chore: add yodap-dg to CODEOWNERS +- chore: archive gh issues + + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-11-16.187.issue.open.md b/issues/2023-11-16.187.issue.open.md new file mode 100644 index 0000000..50eef6e --- /dev/null +++ b/issues/2023-11-16.187.issue.open.md @@ -0,0 +1,31 @@ +# [\#187 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/187) `open`: [FEEDBACK]: Sync attack names between LLMT10 and MLT10 where appropriate +**Labels**: `issues/general`, `issues/triage` + + +#### [kapsolas](https://github.com/kapsolas) opened issue at [2023-11-16 22:16](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/187): + +### Type + +Suggestions for Improvement + +### What would you like to report? + +I would like to make the suggestion that we consolidate the terms used in the LLM and ML top 10 documents. + +Many of the top 10 items in each are closely related or even the same. +Where possible, the same term should be used (i.e. Model Theft vs Model Stealing, Data Poisoning Attack vs Training data Poisoning). + +Thanks! + +### Code of Conduct + +- [X] I agree to follow this project's Code of Conduct + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-11-17.188.issue.open.md b/issues/2023-11-17.188.issue.open.md new file mode 100644 index 0000000..c5c01eb --- /dev/null +++ b/issues/2023-11-17.188.issue.open.md @@ -0,0 +1,30 @@ +# [\#188 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/188) `open`: [FEEDBACK]: Include MLOps vulnerabilties somewhere in the Supply Chain Security category +**Labels**: `issues/general`, `issues/triage` + + +#### [mik0w](https://github.com/mik0w) opened issue at [2023-11-17 10:26](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/188): + +### Type + +Suggestions for Improvement + +### What would you like to report? + +**Context** +One of the parts of the supply chain in modern ML systems is MLOps software - like i.e. MLFlow, Prefect etc. Those systems are vulnerable to classic web based attacks and they seem to be "misconfured by default". I've described it here: https://hackstery.com/2023/10/13/no-one-is-prefect-is-your-mlops-infrastructure-leaking-secrets/ or here: https://github.com/logspace-ai/langflow/issues/1145 + +**Suggestion for improvement** +I'd suggest including MLOps-related vulnerabilities in the ML06 (or maybe in some other categories as well? I am open for suggestions). + +### Code of Conduct + +- [X] I agree to follow this project's Code of Conduct + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).] diff --git a/issues/2023-11-23.189.issue.open.md b/issues/2023-11-23.189.issue.open.md new file mode 100644 index 0000000..8d79663 --- /dev/null +++ b/issues/2023-11-23.189.issue.open.md @@ -0,0 +1,30 @@ +# [\#189 Issue](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/189) `open`: [FEEDBACK]: Include a page with a brief descriptions of each of the vulnerabilities +**Labels**: `issues/general`, `issues/triage` + + +#### [mik0w](https://github.com/mik0w) opened issue at [2023-11-23 12:08](https://github.com/OWASP/www-project-machine-learning-security-top-10/issues/189): + +### Type + +Suggestions for Improvement + +### What would you like to report? + +For example in Top10 for LLM there's this page with a summary of each of the vulnerabilities, which I think would be pretty useful to have in Top10 for ML as well. + +Sometimes when you e.g. work on some slides for a presentation, you just want to get a short summary of each of the vulnerabilities. In my opinion including such a page in Top10 for ML would be an improvement: + +![summary](https://github.com/OWASP/www-project-machine-learning-security-top-10/assets/64902909/0bc2b1c8-43a0-4a5d-b549-71cf83e897c1) + +### Code of Conduct + +- [X] I agree to follow this project's Code of Conduct + + + + +------------------------------------------------------------------------------- + + + +[Export of Github issue for [OWASP/www-project-machine-learning-security-top-10](https://github.com/OWASP/www-project-machine-learning-security-top-10).]