Related papers: Pyramid Adversarial Training Improves ViT Performa…

Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian…

Patch attacks, one of the most threatening forms of physical attack in adversarial examples, can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous region. Certifiable patch defense can guarantee…

Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most…

Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches to training robust models against…

Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range of vision applications, such as image classification, object detection and semantic image segmentation. In comparison to convolutional…

A human's attention can intuitively adapt to corrupted areas of an image by recalling a similar uncorrupted image they have previously seen. This observation motivates us to improve the attention of adversarial images by considering their…

Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a…

Deep learning methods have shown impressive results for a variety of medical problems over the last few years. However, datasets tend to be small due to time-consuming annotation. As datasets with different patients are often very…

Neural networks are susceptible to adversarial examples-small input perturbations that cause models to fail. Adversarial training is one of the solutions that stops adversarial examples; models are exposed to attacks during training and…

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

Extensive research has demonstrated that deep neural networks (DNNs) are prone to adversarial attacks. Although various defense mechanisms have been proposed for image classification networks, fewer approaches exist for video-based models…

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces. Despite their effectiveness, these models remain vulnerable…

In this paper, we develop improved techniques for defending against adversarial examples at scale. First, we implement the state of the art version of adversarial training at unprecedented scale on ImageNet and investigate whether it…

Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i.e., accuracy on natural samples has reduced significantly. In this study, we reveal…

We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical…

In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce…

A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the…

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating…

Most existing works focus on improving robustness against adversarial attacks bounded by a single $l_p$ norm using adversarial training (AT). However, these AT models' multiple-norm robustness (union accuracy) is still low, which is crucial…

Deep learning-based construction-site image analysis has recently made great progress with regard to accuracy and speed, but it requires a large amount of data. Acquiring sufficient amount of labeled construction-image data is a…