相关论文: VCAT: Vulnerability-aware and Curiosity-driven Adv…

Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected…

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively…

Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention. Recent work showed that ViTs are also vulnerable to adversarial examples like CNNs. To build robust ViTs, an intuitive…

Recently, deep learning has been applied to many security-sensitive applications, such as facial authentication. The existence of adversarial examples hinders such applications. The state-of-the-art result on defense shows that adversarial…

Benefiting from large-scale pre-training, we have witnessed significant performance boost on the popular Visual Question Answering (VQA) task. Despite rapid progress, it remains unclear whether these state-of-the-art (SOTA) models are…

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

While automated vehicles (AVs) are expected to revolutionize future transportation systems, emerging AV technologies open a door for malicious actors to compromise intelligent vehicles. As the first generation of AVs, adaptive cruise…

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…

Connected and Autonomous Vehicles (CAVs) are transforming modern transportation by enabling cooperative applications such as vehicle platooning, where multiple vehicles travel in close formation to improve efficiency and safety. However,…

Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…

Adversarial Training (AT) and Virtual Adversarial Training (VAT) are the regularization techniques that train Deep Neural Networks (DNNs) with adversarial examples generated by adding small but worst-case perturbations to input examples. In…

Trajectory prediction is a key element of autonomous vehicle systems, enabling them to anticipate and react to the movements of other road users. Evaluating the robustness of prediction models against adversarial attacks is essential to…

With the increasing prevalence of autonomous vehicles (AVs), their vulnerability to various types of attacks has grown, presenting significant security challenges. In this paper, we propose a reinforcement learning (RL)-based approach for…

Autonomous vehicles (AVs) rely on complex perception and communication systems, making them vulnerable to adversarial attacks that can compromise safety. While simulation offers a scalable and safe environment for robustness testing,…

Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. However, most existing AT methods adopt a specific attack to craft adversarial examples,…

Adversarial attacks are often considered as threats to the robustness of Deep Neural Networks (DNNs). Various defending techniques have been developed to mitigate the potential negative impact of adversarial attacks against task…

Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks, raising concerns about the application of such models to risk-sensitive tasks such as autonomous…

In response to the threat of adversarial examples, adversarial training provides an attractive option for enhancing the model robustness by training models on online-augmented adversarial examples. However, most of the existing adversarial…

While adversarial neural networks have been shown successful for static image attacks, very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous…