warisgill / FedDefender
FedDefender is a novel defense mechanism designed to safeguard Federated Learning from the poisoning attacks (i.e., backdoor attacks).
☆12Updated 6 months ago
Alternatives and similar repositories for FedDefender:
Users that are interested in FedDefender are comparing it to the libraries listed below
- A backdoor defense for federated learning via isolated subspace training (NeurIPS2023)☆20Updated last year
- 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".☆30Updated 2 years ago
- Adversarial attacks and defenses against federated learning.☆15Updated last year
- PyTorch implementation of Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance☆33Updated 3 months ago
- Official repository of the paper "Dynamic Defense Against Byzantine Poisoning Attacks in Federated Learning".☆11Updated 2 years ago
- The official code of KDD22 paper "FLDetecotor: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clien…☆74Updated last year
- ☆11Updated last year
- [Usenix Security 2024] Official code implementation of "BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federa…☆30Updated 4 months ago
- ☆54Updated last year
- [ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning☆51Updated last month
- ☆38Updated 3 years ago
- Github Repo for AAAI 2023 paper: On the Vulnerability of Backdoor Defenses for Federated Learning☆35Updated last year
- Federated Learning and Membership Inference Attacks experiments on CIFAR10☆20Updated 5 years ago
- Code implementation of the paper "Federated Unlearning: How to Efficiently Erase a Client in FL?" published at UpML (part of ICML 2022)☆33Updated 2 years ago
- ☆67Updated 2 years ago
- reproduce the FLTrust model based on the paper "FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping"☆28Updated 2 years ago
- This is the code for our paper `Robust Federated Learning with Attack-Adaptive Aggregation' accepted by FTL-IJCAI'21.☆43Updated last year
- IBA: Towards Irreversible Backdoor Attacks in Federated Learning (Poster at NeurIPS 2023)☆32Updated last year
- This is a simple backdoor model for federated learning.We use MNIST as the original data set for data attack and we use CIFAR-10 data set…☆14Updated 4 years ago
- ☆54Updated 3 years ago
- ☆17Updated 2 years ago
- Multi-metrics adaptively identifies backdoors in Federated learning☆24Updated last year
- Membership inference against Federated learning.☆9Updated 3 years ago
- ☆10Updated last year
- ICML 2022 code for "Neurotoxin: Durable Backdoors in Federated Learning" https://arxiv.org/abs/2206.10341☆67Updated last year
- ☆47Updated last year
- Backdoor detection in Federated learning with similarity measurement☆22Updated 2 years ago
- The implementatioin code of paper: “A Practical Clean-Label Backdoor Attack with Limited Information in Vertical Federated Learning”☆11Updated last year
- ☆25Updated 11 months ago