Year: 2025
Type: preprint
Abstract: The adoption of reinforcement learning for critical infrastructure defense introduces a vulnerability where sophisticated attackers can strategically exploit the defense algorithm's learning dynamics. While prior work addresses this vulnerability in the context of repeated normal-form games, its extension to the stochastic games remains an open research gap. We close this gap by examining stochastic security games between an RL defender and an omniscient attacker, utilizing a tractable linear influence network model. To overcome the structural limitations of prior methods, we propose and apply neuro-dynamic programming. Our experimental results demonstrate that the omniscient attacker can significantly outperform a naive defender, highlighting the critical vulnerability introduced by the learning dynamics and the effectiveness of the proposed strategy.
Source: arXiv (Cornell University)
Authors: Arslantas, Yuksel, Donmez, Ahmed Said, Yuceel, Ege, Sayin, Muhammed O.
Institutions: Bilkent University, University of Illinois Urbana-Champaign
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1078920935, G2023507843, G37936467
OpenAlex ID: W7108941344
Cites:
Cited by:
Related to: