Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization
Abstract
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 works, which develop robust aggregation schemes by employing robust variations of the mean. We present a new attack based on sensitivity curve maximization (SCM), and demonstrate that it is able to disrupt existing robust aggregation schemes by injecting small, but effective perturbations.
Cite
@article{arxiv.2304.14024,
title = {Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization},
author = {Christian A. Schroth and Stefan Vlaski and Abdelhak M. Zoubir},
journal= {arXiv preprint arXiv:2304.14024},
year = {2023}
}