warisgill / TraceFL
TraceFL is a novel mechanism for Federated Learning that achieves interpretability by tracking neuron provenance. It identifies clients responsible for global model predictions, achieving 99% accuracy across diverse datasets (e.g., medical imaging) and neural networks (e.g., GPT).
☆9Updated 5 months ago
Alternatives and similar repositories for TraceFL:
Users that are interested in TraceFL are comparing it to the libraries listed below
- FedDefender is a novel defense mechanism designed to safeguard Federated Learning from the poisoning attacks (i.e., backdoor attacks).☆15Updated 9 months ago
- PyTorch implementation of Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance☆33Updated 6 months ago
- fully ready experiments☆37Updated 2 years ago
- Official implementation of "FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective"