arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1606.08883cs.DCcs.LG
收藏

非贝叶斯学习对对抗攻击的防御

Defending Non-Bayesian Learning against Adversarial Attacks

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-尚佩恩分校)

Lili Su, Nitin H. Vaidya

摘要:

本文讨论了多智能体网络上的非贝叶斯学习问题,其中智能体反复收集关于世界未知状态的部分信息观测,并尝试协作学习真实状态。我们专注于对抗代理对基于共识的非贝叶斯学习性能的影响,其中非故障代理将局部学习更新与共识原语相结合。特别是,我们考虑的情况下,一个未知的子集的代理遭受拜占庭故障-代理遭受拜占庭故障的行为任意。提出了两种不同的学习规则。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑