The rapid growth in the number of devices and their connectivity has enlarged the attack
surface and made cyber systems more vulnerable. As attackers become increasingly …

Machine learning (ML) has been universally adopted for automated decisions in a variety of
fields, including recognition and classification applications, recommendation systems …

We study the robustness of reinforcement learning (RL) with adversarially perturbed state
observations, which aligns with the setting of many adversarial attacks to deep …

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount
of offline data for complex decision-making tasks. Due to the distribution shift issue, current …

We investigate the problem of corruption robustness in offline reinforcement learning (RL)
with general function approximation, where an adversary can corrupt each sample in the …

We study a security threat to reinforcement learning where an attacker poisons the learning
environment to force the agent into executing a target policy chosen by the attacker. As a …

A trustworthy reinforcement learning algorithm should be competent in solving challenging
real-world problems, including {robustly} handling uncertainties, satisfying {safety} …

In a two-player deep reinforcement learning task, recent work shows an attacker could learn
an adversarial policy that triggers a target agent to perform poorly and even react in an …

Due to the broad range of applications of multi-agent reinforcement learning (MARL),
understanding the effects of adversarial attacks against MARL model is essential for the safe …

We study the design of explicable reward functions for a reinforcement learning agent while
guaranteeing that an optimal policy induced by the function belongs to a set of target …