Related papers: X-Transfer Attacks: Towards Super Transferable Adv…

Deep networks are highly vulnerable to adversarial attacks, yet conventional attack methods utilize static adversarial perturbations that induce fixed mispredictions. In this work, we exploit an overlooked property of adversarial…

As a pivotal technique for improving the defense of deep models, adversarial robustness transfer via distillation has demonstrated remarkable success in conventional image classification tasks. However, this paradigm encounters critical…

In the context of medical artificial intelligence, this study explores the vulnerabilities of the Pathology Language-Image Pretraining (PLIP) model, a Vision Language Foundation model, under targeted attacks. Leveraging the Kather Colon…

In this paper, we propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains under conditions of limited training data and significant visual differences. The main idea behind our…

Transferable adversarial attacks against Deep neural networks (DNNs) have received broad attention in recent years. An adversarial example can be crafted by a surrogate model and then attack the unknown target model successfully, which…

While vision-language pre-training model (VLP) has shown revolutionary improvements on various vision-language (V+L) tasks, the studies regarding its adversarial robustness remain largely unexplored. This paper studied the adversarial…

Contrastive Language-Image Pre-training (CLIP) models have demonstrated superior performance across various visual tasks including medical image classification. However, fairness concerns, including demographic biases, have received limited…

Code models are increasingly adopted in software development but remain vulnerable to backdoor attacks via poisoned training data. Existing backdoor attacks on code models face a fundamental trade-off between transferability and…

Deep neural networks have achieved unprecedented success on diverse vision tasks. However, they are vulnerable to adversarial noise that is imperceptible to humans. This phenomenon negatively affects their deployment in real-world…

Universal adversarial perturbations (UAPs) have garnered significant attention due to their ability to undermine deep neural networks across multiple inputs using a single noise pattern. Evolutionary algorithms offer a promising approach to…

The security of models based on new architectures such as MLP-Mixer and ViTs needs to be studied urgently. However, most of the current researches are mainly aimed at the adversarial attack against ViTs, and there is still relatively little…

Deep neural networks (DNNs) can be easily fooled by adding human imperceptible perturbations to the images. These perturbed images are known as `adversarial examples' and pose a serious threat to security and safety critical systems. A…

Vision-language models (VLMs) seamlessly integrate visual and textual data to perform tasks such as image classification, caption generation, and visual question answering. However, adversarial images often struggle to deceive all prompts…

Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…

Vision-language pre-training models (VLPs) have exhibited revolutionary improvements in various vision-language tasks. In VLP, some adversarial attacks fool a model into false or absurd classifications. Previous studies addressed these…

X-ray imagery security screening is essential to maintaining transport security against a varying profile of threat or prohibited items. Particular interest lies in the automatic detection and classification of weapons such as firearms and…

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal…

Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats…

Despite their great success in image recognition tasks, deep neural networks (DNNs) have been observed to be susceptible to universal adversarial perturbations (UAPs) which perturb all input samples with a single perturbation vector.…