Score: 1

Omniscient Attacker in Stochastic Security Games with Interdependent Nodes

Published: December 4, 2025 | arXiv ID: 2512.04561v1

By: Yuksel Arslantas , Ahmed Said Donmez , Ege Yuceel and more

Potential Business Impact:

Makes smart defenses vulnerable to clever attackers.

Business Areas:
Intelligent Systems Artificial Intelligence, Data and Analytics, Science and Engineering

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.

Country of Origin
πŸ‡ΉπŸ‡· πŸ‡ΊπŸ‡Έ Turkey, United States

Page Count
13 pages

Category
Computer Science:
CS and Game Theory