The success of machine learning is fueled by the increasing availability of computing power
and large training datasets. The training data is used to learn new models or update existing …

Machine Learning (ML) has emerged as an attractive and viable technique to provide
effective solutions for a wide range of application domains. An important application domain …

In Autonomous Driving (AD) systems, perception is both security and safety critical. Despite
various prior studies on its security issues, all of them only consider attacks on camera-or …

Deep learning has substantially boosted the performance of Monocular Depth Estimation
(MDE), a critical component in fully vision-based autonomous driving (AD) systems (eg …

A deep reinforcement learning (DRL) agent observes its states through observations, which
may contain natural measurement errors or adversarial noises. Since the observations …

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

Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be
particularly vulnerable to adversarial perturbations on input observations. Therefore, it is …

Recent studies have shown that DNNs are vulnerable to adversarial examples which are
manipulated instances targeting to mislead DNNs to make incorrect predictions. Currently …

Deep reinforcement learning (DRL) has numerous applications in the real world, thanks to
its ability to achieve high performance in a range of environments with little manual …

Evaluating the worst-case performance of a reinforcement learning (RL) agent under the
strongest/optimal adversarial perturbations on state observations (within some constraints) …