Related papers: OmniPatch: A Universal Adversarial Patch for ViT-C…

Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks.…

While adversarial training has been extensively studied for ResNet architectures and low resolution datasets like CIFAR, much less is known for ImageNet. Given the recent debate about whether transformers are more robust than convnets, we…

Adversarial attacks in deep learning models, especially for safety-critical systems, are gaining more and more attention in recent years, due to the lack of trust in the security and robustness of AI models. Yet the more primitive…

We find that the well-trained victim models (VMs), against which the attacks are generated, serve as fundamental prerequisites for adversarial attacks, i.e. a segmentation VM is needed to generate attacks for segmentation. In this context,…

Vision transformers (ViTs) have significantly changed the computer vision landscape and have periodically exhibited superior performance in vision tasks compared to convolutional neural networks (CNNs). Although the jury is still out on…

Recent advances in attention-based networks have shown that Vision Transformers can achieve state-of-the-art or near state-of-the-art results on many image classification tasks. This puts transformers in the unique position of being a…

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they remain adversarial even against other models. Although great efforts have been delved into the…

Thanks to the excellent learning capability of deep convolutional neural networks (CNN), monocular depth estimation using CNNs has achieved great success in recent years. However, depth estimation from a monocular image alone is essentially…

The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the adversarial robustness of embodied vision navigation is…

Segmentation models exhibit significant vulnerability to adversarial examples in white-box settings, but existing adversarial attack methods often show poor transferability across different segmentation models. While some researchers have…

To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input data instead of…

Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs). Investigating the generation of high-transferability…

Deep learning models have shown remarkable success in dermatological image analysis, offering potential for automated skin disease diagnosis. Previously, convolutional neural network(CNN) based architectures have achieved immense popularity…

It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, generally exist for deep networks to fail on image classification. In this paper, we extend adversarial examples…

Deep neural networks (DNNs) can be easily fooled by adding human imperceptible perturbations to the images. These perturbed images are known as `adversarial examples' and pose a serious threat to security and safety critical systems. A…

We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of…

Segment Anything Models (SAM) have made significant advancements in image segmentation, allowing users to segment target portions of an image with a single click (i.e., user prompt). Given its broad applications, the robustness of SAM…

Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this…

We consider the problem of unsupervised domain adaptation in semantic segmentation. The key in this campaign consists in reducing the domain shift, i.e., enforcing the data distributions of the two domains to be similar. A popular strategy…

Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger misclassifications. Most existing defenses assume a single patch…