A Talpur, M Gurusamy - IEEE Communications Surveys & …, 2021 - ieeexplore.ieee.org
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 …
Y Liang, Y Sun, R Zheng… - Advances in Neural …, 2022 - proceedings.neurips.cc
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) …