相关论文: Dynamic Dual-level Defense Routing for Continual A…

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

As the applications of deep reinforcement learning (DRL) in wireless communications grow, sensitivity of DRL based wireless communication strategies against adversarial attacks has started to draw increasing attention. In order to address…

In this paper, we study fast training of adversarially robust models. From the analyses of the state-of-the-art defense method, i.e., the multi-step adversarial training, we hypothesize that the gradient magnitude links to the model…

Federated recommendation (FedRec) preserves user privacy by enabling decentralized training of personalized models, but this architecture is inherently vulnerable to adversarial attacks. Significant research has been conducted on targeted…

Gradient-based adversarial attacks on deep neural networks pose a serious threat, since they can be deployed by adding imperceptible perturbations to the test data of any network, and the risk they introduce cannot be assessed through the…

Deep Reinforcement Learning (DRL) has numerous applications in the real world thanks to its outstanding ability in quickly adapting to the surrounding environments. Despite its great advantages, DRL is susceptible to adversarial attacks,…

Many challenging real-world problems require the deployment of ensembles multiple complementary learning models to reach acceptable performance levels. While effective, applying the entire ensemble to every sample is costly and often…

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples…

In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the problem of mapless navigation for a terrestrial mobile robot. Our methodology focus on comparing a Deep-RL technique based on the Deep Q-Network…

We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and prove that globally optimal goal-reaching policies can be…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this paper, we identify an overlooked problem of adversarial training…

Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and…

Smart grids are designed to efficiently handle variable power demands, especially for large loads, by real-time monitoring, distributed generation and distribution of electricity. However, the grid's distributed nature and the internet…

Model-based Vol/VAR optimization method is widely used to eliminate voltage violations and reduce network losses. However, the parameters of active distribution networks(ADNs) are not onsite identified, so significant errors may be involved…

Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study…

In this paper, we propose a defence strategy to improve adversarial robustness by incorporating hidden layer representation. The key of this defence strategy aims to compress or filter input information including adversarial perturbation.…

Intrusion Detection Systems (IDS) are critical components in safeguarding 5G/6G networks from both internal and external cyber threats. While traditional IDS approaches rely heavily on signature-based methods, they struggle to detect novel…