all InfoSec news
Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks. (arXiv:2302.01677v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
In this work, besides improving prediction accuracy, we study whether
personalization could bring robustness benefits to backdoor attacks. We conduct
the first study of backdoor attacks in the pFL framework, testing 4 widely used
backdoor attacks against 6 pFL methods on benchmark datasets FEMNIST and
CIFAR-10, a total of 600 experiments. The study shows that pFL methods with
partial model-sharing can significantly boost robustness against backdoor
attacks. In contrast, pFL methods with full model-sharing do not show
robustness. To analyze …
accuracy attacks backdoor backdoor attacks benchmark benefits datasets federated learning framework partial prediction robustness sharing study testing work