A Framework For Adversarial Analysis Of Decision Support Systems Prior To Deployment

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybissey2025a

Related papers

• Learning To Cope With Adversarial Attacks (2019)0.00
• Robust Deep Reinforcement Learning Through Adversarial Attacks And Training : A Survey (2024)0.00
• Deep Reinforcement Learning For Autonomous Cyber Defence: A Survey (2023)0.00
• Unveiling The Black Box: A Multi-layer Framework For Explaining Reinforcement Learning-based Cyber Agents (2025)0.00
• Query-based Targeted Action-space Adversarial Policies On Deep Reinforcement Learning Agents (2020)0.00
• Adversarial Inception Backdoor Attacks Against Reinforcement Learning (2024)0.00
• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Reinforcement Learning Under Threats (2018)9.59