相关论文: Revisiting Adversarial Training for ImageNet: Arch…

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…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Deep learning models are prone to being fooled by imperceptible perturbations known as adversarial attacks. In this work, we study how equipping models with Test-time Transformation Ensembling (TTE) can work as a reliable defense against…

Recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represents an input image as a…

The Vision Transformer has emerged as a powerful tool for image classification tasks, surpassing the performance of convolutional neural networks (CNNs). Recently, many researchers have attempted to understand the robustness of Transformers…

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.…

With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…

Batch Normalization (BatchNorm) is effective for improving the performance and accelerating the training of deep neural networks. However, it has also shown to be a cause of adversarial vulnerability, i.e., networks without it are more…

Lifted neural networks (i.e. neural architectures explicitly optimizing over respective network potentials to determine the neural activities) can be combined with a type of adversarial training to gain robustness for internal as well as…

Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretrained classifier, showing that even in the linear case the…

Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training data. However, this way of adversarial injection inevitably…

We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. Attack vectors cause not only image classifiers to fail, but also collaterally disrupt incidental structure in the image. We demonstrate…

Adversarial perturbations are imperceptible changes to input pixels that can change the prediction of deep learning models. Learned weights of models robust to such perturbations are previously found to be transferable across different…

The adversarial robustness of a neural network mainly relies on two factors: model capacity and anti-perturbation ability. In this paper, we study the anti-perturbation ability of the network from the feature maps of convolutional layers.…

We investigate the robustness properties of ResNeXt class image recognition models trained with billion scale weakly supervised data (ResNeXt WSL models). These models, recently made public by Facebook AI, were trained with ~1B images from…

Vision Transformers (ViTs) have demonstrated impressive performance across a range of applications, including many safety-critical tasks. However, their unique architectural properties raise new challenges and opportunities in adversarial…

Adversarial examples for neural network image classifiers are known to be transferable: examples optimized to be misclassified by a source classifier are often misclassified as well by classifiers with different architectures. However,…

Adversarial attacks and defenses have gained increasing interest on computer vision systems in recent years, but as of today, most investigations are limited to images. However, many artificial intelligence models actually handle…

Adversarial examples, crafted by adding perturbations imperceptible to humans, can deceive neural networks. Recent studies identify the adversarial transferability across various models, \textit{i.e.}, the cross-model attack ability of…

Defending against physical adversarial attacks is a rapidly growing topic in deep learning and computer vision. Prominent forms of physical adversarial attacks, such as overlaid adversarial patches and objects, share similarities with…