Related papers: Robust Deep Reinforcement Learning with Adversaria…
In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A…
Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and non-smoothness of normally obtained loss landscapes.…
Deep reinforcement learning (RL) approaches have been broadly applied to a large number of robotics tasks, such as robot manipulation and autonomous driving. However, an open problem in deep RL is learning policies that are robust to…
Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of defense methods have been proposed to train adversarially robust DNNs, among which adversarial training has demonstrated promising results. However,…
Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding…
In this work, we point out the problem of observed adversaries for deep policies. Specifically, recent work has shown that deep reinforcement learning is susceptible to adversarial attacks where an observed adversary acts under…
In real-world tasks, reinforcement learning (RL) agents frequently encounter situations that are not present during training time. To ensure reliable performance, the RL agents need to exhibit robustness against worst-case situations. The…
Currently, reinforcement learning (RL), especially deep RL, has received more and more attention in the research area. However, the security of RL has been an obvious problem due to the attack manners becoming mature. In order to defend…
As a form of artificial intelligence (AI) technology based on interactive learning, deep reinforcement learning (DRL) has been widely applied across various fields and has achieved remarkable accomplishments. However, DRL faces certain…
Deep reinforcement learning (DRL) is vulnerable to adversarial perturbations. Adversaries can mislead the policies of DRL agents by perturbing the state of the environment observed by the agents. Existing attacks are feasible in principle,…
Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives,…
Adversarial training is an effective method to boost model robustness to malicious, adversarial attacks. However, such improvement in model robustness often leads to a significant sacrifice of standard performance on clean images. In many…
The forecast of electrical loads is essential for the planning and operation of the power system. Recently, advances in deep learning have enabled more accurate forecasts. However, deep neural networks are prone to adversarial attacks.…
Robots have limited adaptation ability compared to humans and animals in the case of damage. However, robot damages are prevalent in real-world applications, especially for robots deployed in extreme environments. The fragility of robots…
In deep Reinforcement Learning (RL), the learning rate critically influences both stability and performance, yet its optimal value shifts during training as the environment and policy evolve. Standard decay schedulers assume monotonic…
Assigning importance weights to adversarial data has achieved great success in training adversarially robust networks under limited model capacity. However, existing instance-reweighted adversarial training (AT) methods heavily depend on…
Deep reinforcement learning (DRL) has been used to learn effective heuristics for solving complex combinatorial optimisation problem via policy networks and have demonstrated promising performance. Existing works have focused on solving…
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…
Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few…