FLPoison: Benchmarking Poisoning Attacks and Defenses in Federated Learning
[ACSAC '24] FedCAP: Robust Federated Learning via Customized Aggregation and Personalization
Official Pytorch Implementation for ECCV‘24 "SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks"
Zero-knowledge federated learning with lattice-based encryption and homomorphic aggregation for privacy-preserving, quantum-secure AI.
ECDSA-based cryptographic verification system for detecting poisoning attacks in federated learning
Krum, the library
The uv of federated learning — Rust core for aggregation and attack sim, Python API for HuggingFace, PEFT, and PyTorch.
Privacy-Preserving Federated Learning Intrusion Detection System | Byzantine-robust aggregation | Differential Privacy | SHAP/LIME explainability | Real-time dashboard
Reproduction of "Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering" (Xu et al., 2022) — implementing Multi-Krum, SignGuard, A Little Is Enough, and Fall of Empires in PyTorch. Also includes MoNNA (Farhadkhani et al., ICML 2023).
Break and defend federated learning in one JSON config — 9 aggregation strategies, 11 attack types, 22 datasets.
Add a description, image, and links to the byzantine-robust topic page so that developers can more easily learn about it.
To associate your repository with the byzantine-robust topic, visit your repo's landing page and select "manage topics."