相关论文: Transferable Physical-World Adversarial Patches Ag…

Despite modifying only a small localized input region, adversarial patches can drastically change the prediction of computer vision models. However, prior methods either cannot perform satisfactorily under targeted attack scenarios or fail…

Perception module of Autonomous vehicles (AVs) are increasingly susceptible to be attacked, which exploit vulnerabilities in neural networks through adversarial inputs, thereby compromising the AI safety. Some researches focus on creating…

Physical adversarial patch (PAP) attacks attach carefully crafted patches to physical objects to manipulate a deployed model. However, existing PAP attacks suffer from several limitations. First, existing patches remain continuously active,…

End-to-end autonomous driving systems have achieved significant progress, yet their adversarial robustness remains largely underexplored. In this work, we conduct a closed-loop evaluation of state-of-the-art autonomous driving agents under…

In recent years, adversarial attacks against deep learning-based object detectors in the physical world have attracted much attention. To defend against these attacks, researchers have proposed various defense methods against adversarial…

Physical adversarial attacks pose a significant practical threat as it deceives deep learning systems operating in the real world by producing prominent and maliciously designed physical perturbations. Emphasizing the evaluation of…

Applications such as autonomous vehicles and medical screening use deep learning models to localize and identify hundreds of objects in a single frame. In the past, it has been shown how an attacker can fool these models by placing an…

In recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end training and often generate noticeable perturbation patches. To…

Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the…

Physical adversarial patches printed on clothing can enable individuals to evade person detectors, but most existing methods prioritize attack effectiveness over stealthiness, resulting in aesthetically unpleasing patches. While generative…

Physical adversarial attacks threaten to fool object detection systems, but reproducible research on the real-world effectiveness of physical patches and how to defend against them requires a publicly available benchmark dataset. We present…

Detection of military assets on the ground can be performed by applying deep learning-based object detectors on drone surveillance footage. The traditional way of hiding military assets from sight is camouflage, for example by using…

Adversarial robustness in LiDAR-based 3D object detection is a critical research area due to its widespread application in real-world scenarios. While many digital attacks manipulate point clouds or meshes, they often lack physical…

Taking into account information across the temporal domain helps to improve environment perception in autonomous driving. However, it has not been studied so far whether temporally fused neural networks are vulnerable to deliberately…

The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against…

A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a…

Vision-Language-Action (VLA) models have achieved revolutionary progress in robot learning, enabling robots to execute complex physical robot tasks from natural language instructions. Despite this progress, their adversarial robustness…

Face recognition is greatly improved by deep convolutional neural networks (CNNs). Recently, these face recognition models have been used for identity authentication in security sensitive applications. However, deep CNNs are vulnerable to…

Intelligent driving systems are vulnerable to physical adversarial attacks on traffic signs. These attacks can cause misclassification, leading to erroneous driving decisions that compromise road safety. Moreover, within V2X networks, such…

Growing at a fast pace, modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Sharing information and distributing workloads allow autonomous agents to better perform tasks…