Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization. (arXiv:2304.14024v1 [cs.LG])

Distributed learning paradigms, such as federated or decentralized learning,
allow a collection of agents to solve global learning and optimization problems
through limited local interactions. Most such strategies rely on a mixture of
local adaptation and aggregation steps, either among peers or at a central
fusion center. Classically, aggregation in distributed learning is based on
averaging, which is statistically efficient, but susceptible to attacks by even
a small number of malicious agents. This observation has motivated a number of
recent …

aggregation attacks center collection decentralized distributed fusion global local malicious optimization problems