Omniscient Attacker in Stochastic Security Games with Interdependent Nodes
By: Yuksel Arslantas , Ahmed Said Donmez , Ege Yuceel and more
Potential Business Impact:
Makes smart defenses vulnerable to clever attackers.
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.
Similar Papers
Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach
Machine Learning (CS)
Makes AI systems impossible to trick.
Adaptive Learning for Moving Target defence: Enhancing Cybersecurity Strategies
CS and Game Theory
Makes computer defenses smarter against hackers.
Bilateral Cognitive Security Games in Networked Control Systems under Stealthy Injection Attacks
Systems and Control
Protects computer systems from sneaky attacks.