Backdoors in DRL: Four Environments Focusing on In-distribution Triggers

2025-05-22 · Chace Ashcraft, Ted Staley, Josh Carney, Cameron Hickert, Kiran Karra, Nathan Drenkow

Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet daily, possibly containing backdoors, and third-party model developers are common. To advance research on backdoor attack mitigation, we develop several trojans for deep reinforcement learning (DRL) agents. We focus on in-distribution triggers, which occur within the agent's natural data distribution, since they pose a more significant security threat than out-of-distribution triggers due to their ease of activation by the attacker during model deployment. We implement backdoor attacks in four reinforcement learning (RL) environments: LavaWorld, Randomized LavaWorld, Colorful Memory, and Modified Safety Gymnasium. We train various models, both clean and backdoored, to characterize these attacks. We find that in-distribution triggers can require additional effort to implement and be more challenging for models to learn, but are nevertheless viable threats in DRL even using basic data poisoning attacks.

📄 PDF Abstract BibTeX arXiv:2505.17248

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackData PoisoningDeep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Manipulating Trajectory Prediction with Backdoors

2023-12-21 · Kaouther Messaoud, Kathrin Grosse, Mickael Chen, Matthieu Cord 외

Autonomous vehicles ought to predict the surrounding agents' trajectories to allow safe maneuvers in uncertain and complex traffic situations. As companies increasingly apply trajectory prediction in the real world, secu…

Autonomous Vehicles Prediction Trajectory Prediction

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

2022-10-07 · Chen Gong, Zhou Yang, Yunpeng Bai, Junda He 외

Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL paradigm because it saves the interacti…

Autonomous Driving Backdoor Attack Offline RL reinforcement-learning+2

Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization

2019-09-06 · Shaofeng Li, Minhui Xue, Benjamin Zi Hao Zhao, Haojin Zhu 외

Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model i…

Backdoor Attacks Against Deep Learning Systems in the Physical World

2020-06-25 · CVPR 2021 1 · Emily Wenger, Josephine Passananti, Arjun Bhagoji, Yuanshun Yao 외

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses…

Deep Learning Transfer Learning

Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space

2024-07-21 · Sanyam Vyas, Chris Hicks, Vasilios Mavroudis

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor trigge…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning