mlsanityData to 14 Oct 2026

A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment

arXiv 2505.21414 ↗First posted 27 May 2025cs.LG cs.AI cs.GTcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 20 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

15 of 20 references.

References · 15

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  5. 2016OpenAI Gymcited by 1,736
  6. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  7. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  8. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  9. 2017Adversarial Attacks on Neural Network Policiescited by 320
  10. 2017Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agentscited by 269
  11. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  12. 2021Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differentlycited by 22
3 more
  1. 2021Network Defense is Not a Gamecited by 6
  2. 2016Deep Reinforcement Learning Discovers Internal Modelscited by 3
  3. 2023Utilizing Explainability Techniques for Reinforcement Learning Model Assurancecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
  2. 2025Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
  3. 2024Analyzing Adversarial Inputs in Deep Reinforcement Learning
  4. 2026SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
  5. 2025Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
  6. 2024Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
  7. 2025Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification
  8. 2025Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems