Poisoning Deep Reinforcement Learning Agents With In-distribution Triggers

Abstract

In this paper, we propose a new data poisoning attack and apply it to deep reinforcement learning agents. Our attack centers on what we call in-distribution triggers, which are triggers native to the data distributions the model will be trained on and deployed in. We outline a simple procedure for embedding these, and other, triggers in deep reinforcement learning agents following a multi-task learning paradigm, and demonstrate in three common reinforcement learning environments. We believe that this work has important implications for the security of deep learning models.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyashcraft2021poisoning

Related papers

• Execute Order 66: Targeted Data Poisoning For Reinforcement Learning (2022)0.00
• Trojdrl: Trojan Attacks On Deep Reinforcement Learning Agents (2019)0.00
• Efficient Reward Poisoning Attacks On Online Deep Reinforcement Learning (2022)0.00
• Black-box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning (2023)0.00
• Online Poisoning Attack Against Reinforcement Learning Under Black-box Environments (2024)0.00
• Adversarial Inception Backdoor Attacks Against Reinforcement Learning (2024)0.00
• Beyond Training-time Poisoning: Component-level And Post-training Backdoors In Deep Reinforcement Learning (2025)0.00
• Policy Teaching In Reinforcement Learning Via Environment Poisoning Attacks (2020)0.00