RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors
Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives, often bypassing traditional reward-based defenses. Prior methods have primarily focused on reducing cumulative rewards; however, rewards are typically too generic to capture complex safety requirements effectively. As a result, focusing solely on reward reduction can lead to suboptimal attack strategies, particularly in safety-critical scenarios where more precise behavior manipulation is needed. To address these challenges, we propose RAT, a method designed for universal, targeted behavior attacks. RAT trains an intention policy that is explicitly aligned with human preferences, serving as a precise behavioral target for the adversary. Concurrently, an adversary manipulates the victim's policy to follow this target behavior. To enhance the effectiveness of these attacks, RAT dynamically adjusts the state occupancy measure within the replay buffer, allowing for more controlled and effective behavior manipulation. Our empirical results on robotic simulation tasks demonstrate that RAT outperforms existing adversarial attack algorithms in inducing specific behaviors. Additionally, RAT shows promise in improving agent robustness, leading to more resilient policies. We further validate RAT by guiding Decision Transformer agents to adopt behaviors aligned with human preferences in various MuJoCo tasks, demonstrating its effectiveness across diverse tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackDeep Reinforcement LearningMuJoCoMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents
Advances in computing resources have resulted in the increasing complexity of cyber-physical systems (CPS). As the complexity of CPS evolved, the focus has shifted from traditional control methods to deep reinforcement l…
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Transfer LearningTrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities ex…
Data PoisoningDeep Reinforcement LearningGeneral Classificationreinforcement-learning+2Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking
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 decre…
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)A Novel Bifurcation Method for Observation Perturbation Attacks on Reinforcement Learning Agents: Load Altering Attacks on a Cyber Physical Power System
Components of cyber physical systems, which affect real-world processes, are often exposed to the internet. Replacing conventional control methods with Deep Reinforcement Learning (DRL) in energy systems is an active are…
continuous-controlContinuous ControlDeep Reinforcement LearningTime Series AnalysisNeutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems
Reinforcement learning (RL) has been an important machine learning paradigm for solving long-horizon sequential decision-making problems under uncertainty. By integrating deep neural networks (DNNs) into the RL framework…
Reinforcement LearningAdversarial AttackAutonomous DrivingStarcraft II