相关论文: OmniPatch: A Universal Adversarial Patch for ViT-C…

Adversarial attacks pose a significant threat to deep learning models, particularly in safety-critical applications like healthcare and autonomous driving. Recently, patch based attacks have demonstrated effectiveness in real-time inference…

The existence of real-world adversarial examples (commonly in the form of patches) poses a serious threat for the use of deep learning models in safety-critical computer vision tasks such as visual perception in autonomous driving. This…

Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial…

Recently demonstrated physical-world adversarial attacks have exposed vulnerabilities in perception systems that pose severe risks for safety-critical applications such as autonomous driving. These attacks place adversarial artifacts in the…

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

Previous studies have shown the vulnerability of vision transformers to adversarial patches, but these studies all rely on a critical assumption: the attack patches must be perfectly aligned with the patches used for linear projection in…

Deep neural networks are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the model's decision. We expose the existence of an intriguing class of spatially bounded, physically realizable,…

Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. % crafted in a similar fashion as CNNs. In this paper, we posit that adversarial…

Deep learning and convolutional neural networks allow achieving impressive performance in computer vision tasks, such as object detection and semantic segmentation (SS). However, recent studies have shown evident weaknesses of such models…

We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations,…

Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper presents a systematic framework for comparative adversarial evaluation across three VLM…

Adversarial examples are inputs with imperceptible perturbations that easily misleading deep neural networks(DNNs). Recently, adversarial patch, with noise confined to a small and localized patch, has emerged for its easy feasibility in…

Vision-Language-Action (VLA) models are vulnerable to adversarial attacks, yet universal and transferable attacks remain underexplored, as most existing patches overfit to a single model and fail in black-box settings. To address this gap,…

Vision transformers (ViTs) process input images as sequences of patches via self-attention; a radically different architecture than convolutional neural networks (CNNs). This makes it interesting to study the adversarial feature space of…

Deep learning drives major advances in autonomous driving (AD), where object detectors are central to perception. However, adversarial attacks pose significant threats to the reliability and safety of these systems, with physical…

This paper introduces an attacking mechanism to challenge the resilience of autonomous driving systems. Specifically, we manipulate the decision-making processes of an autonomous vehicle by dynamically displaying adversarial patches on a…

Recent studies have revealed that vision transformers (ViTs) face similar security risks from adversarial attacks as deep convolutional neural networks (CNNs). However, directly applying attack methodology on CNNs to ViTs has been…

Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and requires careful hyperparameter tuning,…

Adversarial patch attacks pose a severe threat to deep neural networks, yet most existing approaches rely on unrealistic white-box assumptions, untargeted objectives, or produce visually conspicuous patches that limit real-world…

The increasing reliance on machine learning systems has made their security a critical concern. Evasion attacks enable adversaries to manipulate the decision-making processes of AI systems, potentially causing security breaches or…