Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning
This work addresses security risks for robot learning systems, such as autonomous navigation, by exposing vulnerabilities to timing-based attacks, though it is incremental as it builds on existing adversarial attack methods.
The paper tackles the vulnerability of deep reinforcement learning-based navigation systems to strategically-timed adversarial attacks by jamming physical noise patterns, resulting in a significant performance drop in three open-source robot learning environments.
Recent deep neural networks based techniques, especially those equipped with the ability of self-adaptation in the system level such as deep reinforcement learning (DRL), are shown to possess many advantages of optimizing robot learning systems (e.g., autonomous navigation and continuous robot arm control.) However, the learning-based systems and the associated models may be threatened by the risks of intentionally adaptive (e.g., noisy sensor confusion) and adversarial perturbations from real-world scenarios. In this paper, we introduce timing-based adversarial strategies against a DRL-based navigation system by jamming in physical noise patterns on the selected time frames. To study the vulnerability of learning-based navigation systems, we propose two adversarial agent models: one refers to online learning; another one is based on evolutionary learning. Besides, three open-source robot learning and navigation control environments are employed to study the vulnerability under adversarial timing attacks. Our experimental results show that the adversarial timing attacks can lead to a significant performance drop, and also suggest the necessity of enhancing the robustness of robot learning systems.