Uncovering the Connection Between Differential Privacy and Certified Robustness of Federated Learning against Poisoning Attacks. (arXiv:2209.04030v1 [cs.CR])

Federated learning (FL) provides an efficient paradigm to jointly train a
global model leveraging data from distributed users. As the local training data
come from different users who may not be trustworthy, several studies have
shown that FL is vulnerable to poisoning attacks. Meanwhile, to protect the
privacy of local users, FL is always trained in a differentially private way
(DPFL). Thus, in this paper, we ask: Can we leverage the innate privacy
property of DPFL to provide certified robustness …

attacks certified differential privacy federated learning poisoning privacy robustness