Related papers: Give Me Your Attention: Dot-Product Attention Cons…

Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds is becoming increasingly popular for addressing various tasks in this field. Despite remarkable…

Vision Transformers (ViTs) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual…

Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…

Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial images. While many techniques for detecting these attacks…

Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significantly to their high performance. However, it is known to incur…

The vulnerability of deep neural networks (DNNs) to adversarial attack, which is an attack that can mislead state-of-the-art classifiers into making an incorrect classification with high confidence by deliberately perturbing the original…

Adversarial patches are physically realizable localized noise, which are able to hijack Vision Transformers (ViT) self-attention, pulling focus toward a small, high-contrast region and corrupting the class token to force confident…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

This paper discusses the attack feasibility of Remote Adversarial Patch (RAP) targeting face detectors. The RAP that targets face detectors is similar to the RAP that targets general object detectors, but the former has multiple issues in…

In this paper, we investigate the vulnerability of MDE to adversarial patches. We propose a novel \underline{S}tealthy \underline{A}dversarial \underline{A}ttacks on \underline{M}DE (SAAM) that compromises MDE by either corrupting the…

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial…

The adversarial patch attack against image classification models aims to inject adversarially crafted pixels within a restricted image region (i.e., a patch) for inducing model misclassification. This attack can be realized in the physical…

Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the image classification task in image classification. In…

The vulnerability of deep neural networks to adversarial examples, which are crafted maliciously by modifying the inputs with imperceptible perturbations to misled the network produce incorrect outputs, reveals the lack of robustness and…

Adversarial attacks are known to succeed on classifiers, but it has been an open question whether more complex vision systems are vulnerable. In this paper, we study adversarial examples for vision and language models, which incorporate…

Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having…

In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. Attention sink occurs when an excessive amount of attention…

Recent work has shown the potential of transformers for computer vision applications. An image is first partitioned into patches, which are then used as input tokens for the attention mechanism. Due to the expensive quadratic cost of the…

Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet their prediction process remains difficult to interpret because information is propagated through complex interactions across layers and attention heads.…

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the…