Defending Observation Attacks In Deep Reinforcement Learning Via Detection And Denoising

Abstract

Neural network policies trained using Deep Reinforcement Learning (DRL) are well-known to be susceptible to adversarial attacks. In this paper, we consider attacks manifesting as perturbations in the observation space managed by the external environment. These attacks have been shown to downgrade policy performance significantly. We focus our attention on well-trained deterministic and stochastic neural network policies in the context of continuous control benchmarks subject to four well-studied observation space adversarial attacks. To defend against these attacks, we propose a novel defense strategy using a detect-and-denoise schema. Unlike previous adversarial training approaches that sample data in adversarial scenarios, our solution does not require sampling data in an environment under attack, thereby greatly reducing risk during training. Detailed experimental results show that our technique is comparable with state-of-the-art adversarial training approaches.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxiong2022defending

Related papers

• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• Understanding Adversarial Attacks On Observations In Deep Reinforcement Learning (2021)0.00
• Observed Adversaries In Deep Reinforcement Learning (2022)0.00
• Robust Deep Reinforcement Learning Through Adversarial Attacks And Training : A Survey (2024)0.00
• Attacking And Defending Deep Reinforcement Learning Policies (2022)0.00
• Robust Deep Reinforcement Learning Against Adversarial Perturbations On State Observations (2020)0.00
• Real-time Adversarial Perturbations Against Deep Reinforcement Learning Policies: Attacks And Defenses (2021)0.00