Secure Aggregation Is Not All You Need: Mitigating Privacy Attacks with Noise Tolerance in Federated Learning. (arXiv:2211.06324v1 [cs.CR])

Federated learning is a collaborative method that aims to preserve data
privacy while creating AI models. Current approaches to federated learning tend
to rely heavily on secure aggregation protocols to preserve data privacy.
However, to some degree, such protocols assume that the entity orchestrating
the federated learning process (i.e., the server) is not fully malicious or
dishonest. We investigate vulnerabilities to secure aggregation that could
arise if the server is fully malicious and attempts to obtain access to
private, potentially …

attacks federated learning privacy