all InfoSec news
Balancing Privacy and Security in Federated Learning with FedGT: A Group Testing Framework. (arXiv:2305.05506v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
We propose FedGT, a novel framework for identifying malicious clients in
federated learning with secure aggregation. Inspired by group testing, the
framework leverages overlapping groups of clients to detect the presence of
malicious clients in the groups and to identify them via a decoding operation.
The identified clients are then removed from the training of the model, which
is performed over the remaining clients. FedGT strikes a balance between
privacy and security, allowing for improved identification capabilities while
still preserving …
aggregation clients decoding detect federated learning framework identify malicious novel privacy privacy and security security testing testing framework