Defending Non-Bayesian Learning against Adversarial Attacks
It addresses security in distributed learning for applications like sensor networks, but appears incremental as it builds on existing consensus-based methods.
This paper tackles the problem of defending non-Bayesian learning in multi-agent networks against adversarial attacks, specifically Byzantine faults, by proposing two learning rules to mitigate their impact on collaborative state estimation.
This paper addresses the problem of non-Bayesian learning over multi-agent networks, where agents repeatedly collect partially informative observations about an unknown state of the world, and try to collaboratively learn the true state. We focus on the impact of the adversarial agents on the performance of consensus-based non-Bayesian learning, where non-faulty agents combine local learning updates with consensus primitives. In particular, we consider the scenario where an unknown subset of agents suffer Byzantine faults -- agents suffering Byzantine faults behave arbitrarily. Two different learning rules are proposed.