"<italic>FLPurifier</italic>: Backdoor Defense in Federated Learning vi" by Jiale Zhang, Chengcheng Zhu et al.
Recent studies have demonstrated that backdoor attacks can cause a significant security threat to federated learning. Existing defense methods mainly focus on detecting or eliminating the backdoor patterns after the model is backdoored. However, these methods either cause model performance degradation or heavily rely on impractical assumptions, such as labeled clean data, which exhibit limited effectiveness in federated learning. To this end, we propose FLPurifier, a novel backdoor defense method in federated learning that can effectively purify the possible backdoor attributes before federate...
Source: uow.edu.au