Defending Non-Bayesian Learning against Adversarial Attacks

2016/06/28 by Lili Su, Su, Lili, Nitin H. Vaidya +1
Computer Science · #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #and Cluster Computing (cs.DC) #cs.DC #cs.LG

paper · pdf · doi:10.48550/arxiv.1606.08883

arxiv created 2016/06/28 · arxiv updated 2016/06/30

Abstract

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.

Related

• Distributed Learning with Adversarial Agents Under Relaxed Network Condition
• A New Approach to Distributed Hypothesis Testing and Non-Bayesian Learning: Improved Learning Rate and Byzantine-Resilience
• Network Fault-tolerant and Byzantine-resilient Social Learning via Collaborative Hierarchical Non-Bayesian Learning
• A New Approach for Distributed Hypothesis Testing with Extensions to Byzantine-Resilience
• Robust Asynchronous and Network-Independent Cooperative Learning