Targeted Adversarial Attacks On Deep Reinforcement Learning Policies Via Model Checking

Abstract

Deep Reinforcement Learning (RL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decreasing the reward, but also in modifying specific temporal logic properties of the policy. This paper presents a metric that measures the exact impact of adversarial attacks against such properties. We use this metric to craft optimal adversarial attacks. Furthermore, we introduce a model checking method that allows us to verify the robustness of RL policies against adversarial attacks. Our empirical analysis confirms (1) the quality of our metric to craft adversarial attacks against temporal logic properties, and (2) that we are able to concisely assess a system's robustness against attacks.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keygross2022targeted

Related papers

• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• Understanding Adversarial Attacks On Observations In Deep Reinforcement Learning (2021)0.00
• Real-time Adversarial Perturbations Against Deep Reinforcement Learning Policies: Attacks And Defenses (2021)0.00
• Robust Deep Reinforcement Learning Against Adversarial Behavior Manipulation (2024)0.00
• Query-based Targeted Action-space Adversarial Policies On Deep Reinforcement Learning Agents (2020)0.00
• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Optimal Attack And Defense For Reinforcement Learning (2023)6.34
• Learning To Cope With Adversarial Attacks (2019)0.00