A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment
Journal:
arXiv
Published Date:
May 27, 2025
Abstract
This paper introduces a comprehensive framework designed to analyze and
secure decision-support systems trained with Deep Reinforcement Learning (DRL),
prior to deployment, by providing insights into learned behavior patterns and
vulnerabilities discovered through simulation. The introduced framework aids in
the development of precisely timed and targeted observation perturbations,
enabling researchers to assess adversarial attack outcomes within a strategic
decision-making context. We validate our framework, visualize agent behavior,
and evaluate adversarial outcomes within the context of a custom-built
strategic game, CyberStrike. Utilizing the proposed framework, we introduce a
method for systematically discovering and ranking the impact of attacks on
various observation indices and time-steps, and we conduct experiments to
evaluate the transferability of adversarial attacks across agent architectures
and DRL training algorithms. The findings underscore the critical need for
robust adversarial defense mechanisms to protect decision-making policies in
high-stakes environments.
