MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks. (arXiv:2207.07941v2 [cs.LG] UPDATED)

Implementations of SGD on distributed systems create new vulnerabilities,
which can be identified and misused by one or more adversarial agents.
Recently, it has been shown that well-known Byzantine-resilient gradient
aggregation schemes are indeed vulnerable to informed attackers that can tailor
the attacks (Fang et al., 2020; Xie et al., 2020b). We introduce MixTailor, a
scheme based on randomization of the aggregation strategies that makes it
impossible for the attacker to be fully informed. Deterministic schemes can be
integrated into …

attacks