all InfoSec news
Mitigating Backdoors in Federated Learning with FLD. (arXiv:2303.00302v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Federated learning allows clients to collaboratively train a global model
without uploading raw data for privacy preservation. This feature, i.e., the
inability to review participants' datasets, has recently been found responsible
for federated learning's vulnerability in the face of backdoor attacks.
Existing defense methods fall short from two perspectives: 1) they consider
only very specific and limited attacker models and unable to cope with advanced
backdoor attacks, such as distributed backdoor attacks, which break down the
global trigger into multiple …
advanced attacks backdoor backdoor attacks backdoors clients data datasets defense distributed federated learning global perspectives preservation privacy responsible review train vulnerability