Tag: federated learning security

FedSPA combines Shapley-value analysis and model parameter similarity to identify malicious clients in federated learning under data poisoning attacks.

Researchers at Donghua University have developed RFLDefense, a layer-wise defense framework that suppresses backdoor attacks in federated learning even when ...

Cryptographers in China have unveiled a new algorithm that dramatically accelerates one of the most persistent bottlenecks in modern encryption, ...

Federated learning has become one of the most consequential architectures in modern machine learning, allowing thousands of devices to collectively ...