Related papers: Decision-based Black-box Attack Against Vision Tra…
Vision transformers rely on a patch token based self attention mechanism, in contrast to convolutional networks. We investigate fundamental differences between these two families of models, by designing a block sparsity based adversarial…
This paper presents a comparison of the performance of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in the task of multi-classifying images containing lesions of psoriasis and diseases similar to it. Models…
Vision Transformer (ViT) is becoming widely popular in automating accurate disease diagnosis in medical imaging owing to its robust self-attention mechanism. However, ViTs remain vulnerable to adversarial attacks that may thwart the…
Vision transformers (ViTs) that model an image as a sequence of partitioned patches have shown notable performance in diverse vision tasks. Because partitioning patches eliminates the image structure, to reflect the order of patches, ViTs…
Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentation and depth…
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…
This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series…
Since their inception, Vision Transformers (ViTs) have emerged as a compelling alternative to Convolutional Neural Networks (CNNs) across a wide spectrum of tasks. ViTs exhibit notable characteristics, including global attention, resilience…
The emergence of vision transformers (ViTs) in image classification has shifted the methodologies for visual representation learning. In particular, ViTs learn visual representation at full receptive field per layer across all the image…
Facial Expression Recognition (FER) in the wild is an extremely challenging task. Recently, some Vision Transformers (ViT) have been explored for FER, but most of them perform inferiorly compared to Convolutional Neural Networks (CNN). This…
The ability of deep neural networks (DNNs) come from extracting and interpreting features from the data provided. By exploiting intermediate features in DNNs instead of relying on hard labels, we craft adversarial perturbation that…
Wide-parameter-space searches for continuous gravitational waves using semi-coherent matched-filter methods require enormous computing power, which limits their achievable sensitivity. Here we explore an alternative search method based on…
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…
Constructing adversarial examples in a black-box threat model injures the original images by introducing visual distortion. In this paper, we propose a novel black-box attack approach that can directly minimize the induced distortion by…
Label noise in medical image classification datasets significantly hampers the training of supervised deep learning methods, undermining their generalizability. The test performance of a model tends to decrease as the label noise rate…
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…
Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical application, particularly…
An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object…
Adversarial attack patches have gained increasing attention due to their practical applicability in physical-world scenarios. However, the bright colors used in attack patches represent a significant drawback, as they can be easily…
Anomaly Detection (AD) and Anomaly Localization (AL) are crucial in fields that demand high reliability, such as medical imaging and industrial monitoring. However, current AD and AL approaches are often susceptible to adversarial attacks…