all InfoSec news
Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning. (arXiv:2206.01888v1 [cs.LG])
June 7, 2022, 1:20 a.m. | Young Wu, Jermey McMahan, Xiaojin Zhu, Qiaomin Xie
cs.CR updates on arXiv.org arxiv.org
We expose the danger of reward poisoning in offline multi-agent reinforcement
learning (MARL), whereby an attacker can modify the reward vectors to different
learners in an offline data set while incurring a poisoning cost. Based on the
poisoned data set, all rational learners using some confidence-bound-based MARL
algorithm will infer that a target policy - chosen by the attacker and not
necessarily a solution concept originally - is the Markov perfect dominant
strategy equilibrium for the underlying Markov Game, hence …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Information Security Engineers
@ D. E. Shaw Research | New York City
Security Engineer, Incident Response
@ Databricks | Remote - Netherlands
Associate Vulnerability Engineer - Mid-Atlantic region (Part-Time)
@ GuidePoint Security LLC | Remote in VA, MD, PA, NC, DE, NJ, or DC
Data Security Architect
@ Accenture Federal Services | Washington, DC
Identity Security Administrator
@ SailPoint | Pune, India