FedRMA: A Robust Federated Learning Resistant to Multiple Poisoning Attacks
Hongyong Xiao, Xutong Mu, Cheng Ke · Journal of Networking and Network Applications · 2024
Federated learning allows clients to collaboratively train models without disclosing local data, yet it faces the threat of poisoning attacks from malicious clients. Existing research has proposed various robust federated learning schemes, but these often consider only a single type of poisoning attack and are inadequate for scenarios where multiple poisoning attacks occur simultaneously. To address this problem, this paper proposes FedRMA, a robust federated learning scheme resistant to multiple poisoning attacks. FedRMA eliminates the need for unrealistic prior knowledge and defends against multiple poisoning attacks by identifying and removing malicious clients. FedRMA adopts the Affinity Propagation clustering algorithm to adaptively partition clients, thereby enhancing its ability to handle multiple poisoning attacks. To mitigate the impact of uncertainty in client data distribution on model selection, FedRMA uses the L-BFGS algorithm to predict the expected global model and uses it to identify malicious clients. We evaluate the performance of FedRMA on the MNIST and CIFAR-10 datasets and compare it with two existing baselines. The experimental results show that FedRMA successfully eliminates the negative impact of multiple poisoning attacks by accurately identifying malicious clients and outperforms the baseline schemes.