A dual-aggregation approach to fortify federated learning against poisoning attacks in IoTs

Today's article comes from the journal Array. The authors are Al Dalaien et al., from the Princess Sumaya University for Technology, in Jordan. In this paper they're focusing on preventing the "poisoning" of federated learning networks. They propose a dual-aggregation defense that uses ensemble learning at both the client and server levels to harden the system while adding almost no computational overhead.

DOI: 10.1016/j.array.2025.100520