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 4 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).☆13Updated 8 months ago
- PyTorch implementation of Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance☆33Updated 5 months ago
- This repository contains the official implementation for the manuscript: Make Landscape Flatter in Differentially Private Federated Lear…☆47Updated last year
- ☆54Updated 2 years ago
- FLPoison: Benchmarking Poisoning Attacks and Defenses in Federated Learning☆16Updated last month
- Differentially Private Federated Learning on Heterogeneous Data☆61Updated 3 years ago
- The official code of KDD22 paper "FLDetecotor: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clien…☆79Updated 2 years ago
- Official implementation of "FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective"…☆84Updated 4 years ago
- ☆11Updated 2 months ago
- Official implementation of "FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective"…☆39Updated 3 years ago
- The code of AAAI-21 paper titled "Defending against Backdoors in Federated Learning with Robust Learning Rate".☆31Updated 2 years ago
- nips23-Dynamic Personalized Federated Learning with Adaptive Differential Privacy☆66Updated 6 months ago
- Federated Learning and Membership Inference Attacks experiments on CIFAR10☆21Updated 5 years ago
- An open source FL implement with dataset(Femnist, Shakespeare, MNIST, Cifar-10 and Fashion-Mnist) using pytorch☆126Updated last year
- Code for NDSS 2021 Paper "Manipulating the Byzantine: Optimizing Model Poisoning Attacks and Defenses Against Federated Learning"☆142Updated 2 years ago
- Federated Adversrial Learning/ Training Framework. A testing ground for conducting relevant research.☆10Updated 2 years ago
- Concealing Sensitive Samples against Gradient Leakage in Federated Learning (AAAI2024)☆8Updated 8 months ago
- Robust aggregation for federated learning with the RFA algorithm.☆48Updated 2 years ago
- FedAvg, FedGKT, FedProx, Gradient Inversion Attack☆15Updated 2 years ago
- An Empirical Study of Federated Unlearning: Efficiency and Effectiveness (Accepted Conference Track Papers at ACML 2023)☆17Updated last year
- PyTorch implementation of Fast-Convergent Federated Learning via Cyclic Aggregation, including FedAvg, FedProx, MOON, and FedRS☆14Updated last year
- ☆14Updated last year
- ☆36Updated last year
- ☆12Updated last year
- IBA: Towards Irreversible Backdoor Attacks in Federated Learning (Poster at NeurIPS 2023)☆36Updated last year
- Code for Data Poisoning Attacks Against Federated Learning Systems☆186Updated 3 years ago
- reproduce the FLTrust model based on the paper "FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping"☆29Updated 2 years ago
- Implementing the algorithm from our paper: "A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in …☆36Updated 10 months ago
- A sybil-resilient distributed learning protocol.☆103Updated last year
- Official implementation of "Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective"☆55Updated last year