TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
This reveals a critical security vulnerability in reinforcement learning systems, with potential impacts on safety-critical applications, though it is incremental by extending known classification attacks to DRL.
The paper demonstrates that deep reinforcement learning agents are vulnerable to Trojan attacks via minimal data poisoning (as low as 0.025% of training data) and reward modification, causing policies to perform normally until triggered and then deteriorate drastically.
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 extend to deep reinforcement learning (DRL) agents and can be exploited by an adversary with access to the training process. In particular, we focus on Trojan attacks that augment the function of reinforcement learning policies with hidden behaviors. We demonstrate that such attacks can be implemented through minuscule data poisoning (as little as 0.025% of the training data) and in-band reward modification that does not affect the reward on normal inputs. The policies learned with our proposed attack approach perform imperceptibly similar to benign policies but deteriorate drastically when the Trojan is triggered in both targeted and untargeted settings. Furthermore, we show that existing Trojan defense mechanisms for classification tasks are not effective in the reinforcement learning setting.