相关论文: Elytra: A Flexible Framework for Securing Large Vi…

Physical adversarial attacks on road signs are continuously exploiting vulnerabilities in modern day autonomous vehicles (AVs) and impeding their ability to correctly classify what type of road sign they encounter. Current models cannot…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which…

As physical adversarial attacks become extensively applied in unearthing the potential risk of security-critical scenarios, especially in dynamic scenarios, their vulnerability to environmental variations has also been brought to light. The…

Despite significant advancements in deep reinforcement learning (DRL)-based autonomous driving policies, these policies still exhibit vulnerability to adversarial attacks. This vulnerability poses a formidable challenge to the practical…

Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce hallucinations, manipulate responses, or bypass safety mechanisms. Existing methods seek to…

We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to change how it…

The rise of computer vision applications in the real world puts the security of the deep neural networks at risk. Recent works demonstrate that convolutional neural networks are susceptible to adversarial examples - where the input images…

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…

Adversarial patch is an important form of real-world adversarial attack that brings serious risks to the robustness of deep neural networks. Previous methods generate adversarial patches by either optimizing their perturbation values while…

Autonomous vehicles must be comprehensively evaluated before deployed in cities and highways. However, most existing evaluation approaches for autonomous vehicles are static and lack adaptability, so they are usually inefficient in…

Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Adversarial Examples (AEs) can deceive Deep Neural Networks (DNNs) and have received a lot of attention recently. However, majority of the research on AEs is in the digital domain and the adversarial patches are static, which is very…

Despite recent advances in autonomous driving systems, accidents such as the fatal Uber crash in 2018 show these systems are still susceptible to edge cases. Such systems must be thoroughly tested and validated before being deployed in the…

Vision foundation models are increasingly employed in autonomous driving systems due to their advanced capabilities. However, these models are susceptible to adversarial attacks, posing significant risks to the reliability and safety of…

Trajectory prediction using deep neural networks (DNNs) is an essential component of autonomous driving (AD) systems. However, these methods are vulnerable to adversarial attacks, leading to serious consequences such as collisions. In this…

The increasing prevalence of adversarial attacks on Artificial Intelligence (AI) systems has created a need for innovative security measures. However, the current methods of defending against these attacks often come with a high computing…

Recent research shows that neural networks models used for computer vision (e.g., YOLO and Fast R-CNN) are vulnerable to adversarial evasion attacks. Most of the existing real-world adversarial attacks against object detectors use an…