Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers
arXiv:2106.07798
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.
arXiv comment4 pages, 1 figure, Published at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems
References in corpus (11)
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Spectral Signatures in Backdoor Attacks
- Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
- PettingZoo: Gym for Multi-Agent Reinforcement Learning
- Blind Backdoors in Deep Learning Models
- NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations
- Weight Poisoning Attacks on Pre-trained Models
- Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
- Natural Backdoor Attack on Text Data
- The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models