Related papers: Rethinking Mixup for Improving the Adversarial Tra…

Masked image modeling (MIM) has gained significant traction for its remarkable prowess in representation learning. As an alternative to the traditional approach, the reconstruction from corrupted images has recently emerged as a promising…

Image Style Transfer (IST) is an interdisciplinary topic of computer vision and art that continuously attracts researchers' interests. Different from traditional Image-guided Image Style Transfer (IIST) methods that require a style…

Deep Neural Networks (DNNs) are widely acknowledged to be susceptible to adversarial examples, wherein imperceptible perturbations are added to clean examples through diverse input transformation attacks. However, these methods originally…

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples,…

While convolutional neural networks (CNNs) have achieved excellent performances in various computer vision tasks, they often misclassify with malicious samples, a.k.a. adversarial examples. Adversarial training is a popular and…

Transferable adversarial attacks optimize adversaries from a pretrained surrogate model and known label space to fool the unknown black-box models. Therefore, these attacks are restricted by the availability of an effective surrogate model.…

Deep neural networks are vulnerable to adversarial examples that mislead models with imperceptible perturbations. In audio, although adversarial examples have achieved incredible attack success rates on white-box settings and black-box…

Vision Transformers (ViTs) have been widely applied in various computer vision and vision-language tasks. To gain insights into their robustness in practical scenarios, transferable adversarial examples on ViTs have been extensively…

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their…

The integration of visual and textual data in Vision-Language Pre-training (VLP) models is crucial for enhancing vision-language understanding. However, the adversarial robustness of these models, especially in the alignment of image-text…

Deep Neural Networks (DNNs) are highly vulnerable to adversarial examples, which pose significant challenges in security-sensitive applications. Among various adversarial attack strategies, input transformation-based attacks have…

Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target…

Recent development of adversarial attacks has proven that ensemble-based methods outperform traditional, non-ensemble ones in black-box attack. However, as it is computationally prohibitive to acquire a family of diverse models, these…

Adversarial attack is commonly regarded as a huge threat to neural networks because of misleading behavior. This paper presents an opposite perspective: adversarial attacks can be harnessed to improve neural models if amended correctly.…

Deep neural networks (DNNs) are threatened by adversarial examples. Adversarial detection, which distinguishes adversarial images from benign images, is fundamental for robust DNN-based services. Image transformation is one of the most…

Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the visual imperceptibility between adversarial examples and…

Multimodal Large Language Models (MLLMs) demonstrate exceptional performance in cross-modality interaction, yet they also suffer adversarial vulnerabilities. In particular, the transferability of adversarial examples remains an ongoing…

The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from attacking DNNs successfully, rather than preventing their…

Adversarial examples' (AE) transferability refers to the phenomenon that AEs crafted with one surrogate model can also fool other models. Notwithstanding remarkable progress in untargeted transferability, its targeted counterpart remains…