Geminio is a VLM-powered gradient inversion attack in federated learning (FL). It allows the adversary (the FL server) to describe the data of value and reconstruct the victim client's private data matching the description.
[NDSS 2025] CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling
Understanding Deep Gradient Leakage via Inversion Influence Functions, NeurIPS 2023
Add a description, image, and links to the gradient-inversion topic page so that developers can more easily learn about it.
To associate your repository with the gradient-inversion topic, visit your repo's landing page and select "manage topics."