Optimal Cost Constrained Adversarial Attacks for Multiple Agent Systems

Ziqing Lu; Guanlin Liu; Lifeng Lai; Weiyu Xu

doi:10.1109/CISS59072.2024.10480189

Back

Conference proceeding

Optimal Cost Constrained Adversarial Attacks for Multiple Agent Systems

Ziqing Lu, Guanlin Liu, Lifeng Lai and Weiyu Xu

2024 58th Annual Conference on Information Sciences and Systems (CISS), pp.1-6

03/13/2024

DOI: 10.1109/CISS59072.2024.10480189

View Online

Abstract

Since many security-related applications use multi-agent reinforcement learning as their underlying algorithms, the study on the adversarial attacks against mutli-agent reinforcement learning systems receives a lot of attention. Finding optimal adversarial attack strategies is an important topic in adversarial attacks on reinforcement learning and the Markov decision process. Previous studies usually assume one all-knowing coordinator (attacker) for whom attacking different recipient (victim) agents incurs uniform costs. However, in important real-world applications, instead of coming from one limitless central attacker, the attacks often need to be performed by distributed attack agents. We formulate the new problem of performing optimal adversarial agent-to-agent attacks using distributed attack agents, in which we impose distinct cost constraints on each different attacker-victim pair. We propose a novel method integrating within-time-step static attack-resource allocation optimization and between-time-step dynamic programming to achieve the optimal adversarial attack in a multi-agent system. Our numerical results show that the proposed attacks can significantly reduce the rewards received by the attacked agents.

Optimization

adversarial attack

Costs

Dynamic programming

Markov decision process

Markov decision processes

Programming

Reinforcement learning

Resource management

Details

Title: Subtitle: Optimal Cost Constrained Adversarial Attacks for Multiple Agent Systems
Creators: Ziqing Lu - University of Iowa
Guanlin Liu - University of California, Davis
Lifeng Lai - University of California, Davis
Weiyu Xu - University of Iowa
Resource Type: Conference proceeding
Publication Details: 2024 58th Annual Conference on Information Sciences and Systems (CISS), pp.1-6
Publisher: IEEE
DOI: 10.1109/CISS59072.2024.10480189
eISSN: 2837-178X
Language: English
Date published: 03/13/2024
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984621259702771

Metrics

2 Record Views