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.

4 pages, 1 figure, Published at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems

References in corpus (3)

• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations
• Weight Poisoning Attacks on Pre-trained Models