Related papers: Transferable Adversarial Attacks on Vision Transfo…
While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input,…
Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples generated from surrogate models often exhibit weak…
Ensemble-based attacks have been proven to be effective in enhancing adversarial transferability by aggregating the outputs of models with various architectures. However, existing research primarily focuses on refining ensemble weights or…
In recent years, there has been a significant trend in deep neural networks (DNNs), particularly transformer-based models, of developing ever-larger and more capable models. While they demonstrate state-of-the-art performance, their growing…
Transfer-based attack adopts the adversarial examples generated on the surrogate model to attack various models, making it applicable in the physical world and attracting increasing interest. Recently, various adversarial attacks have…
Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. As indicated in…
Recently, Vision Transformers (ViTs) have shown competitive performance on image recognition while requiring less vision-specific inductive biases. In this paper, we investigate if such performance can be extended to image generation. To…
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be robust against white-box attacks, but not against black-box…
Deep neural networks are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations to the benign input. After achieving nearly 100% attack success rates in white-box setting, more focus is shifted to…
Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks. Furthermore, malicious adversaries can be deliberately transferred to attack other black-box models. However, existing work has…
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…
In this paper, we ask whether Vision Transformers (ViTs) can serve as an underlying architecture for improving the adversarial robustness of machine learning models against evasion attacks. While earlier works have focused on improving…
Following their success in visual recognition tasks, Vision Transformers(ViTs) are being increasingly employed for image restoration. As a few recent works claim that ViTs for image classification also have better robustness properties, we…
Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across models, enabling…
Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are also of great…
Vector quantization (VQ) underpins modern generative and representation models by turning continuous latents into discrete tokens. Yet hard nearest-neighbor assignments are non-differentiable and are typically optimized with heuristic…
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…
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a…
Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mainly due to the common but often wrong assumption of such…
The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security. Meanwhile, it is very challenging as there is no access to the network architecture or internal weights of the…