相关论文: Enhancing Adversarial Transferability in Visual-La…

Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks. While existing adversarial perturbations are primarily applied to uncompressed images or compressed images…

The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial…

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object…

Adversarial attacks against Deep Neural Networks have been widely studied. One significant feature that makes such attacks particularly powerful is transferability, where the adversarial examples generated from one model can be effective…

Although significant progress has been made in few-shot learning, most of existing few-shot image classification methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability…

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

Despite the strong performance of deep neural networks in modern Web and language applications, they remain vulnerable to adversarial attacks, especially transferable attacks that generate adversarial examples using surrogate models without…

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. Specifically, we advocate a framework in which a direct…

Multi-modal image fusion integrates complementary information from different modalities to produce enhanced and informative images. Although State-Space Models, such as Mamba, are proficient in long-range modeling with linear complexity,…

Recent advances in instruction tuning have led to the development of State-of-the-Art Large Multimodal Models (LMMs). Given the novelty of these models, the impact of visual adversarial attacks on LMMs has not been thoroughly examined. We…

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on…

Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key aspects of VL tasks: multimodal attacks, where both image…

Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the…

Medical contrastive vision-language pre-training (VLP) has demonstrated significant potential in improving performance on downstream tasks. Traditional approaches typically employ contrastive learning, treating paired image-report samples…

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…

Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We…

Video Multimodal Large Language Models (V-MLLMs) have shown impressive capabilities in temporal reasoning and cross-modal understanding, yet their vulnerability to adversarial attacks remains underexplored due to unique challenges: complex…

Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility.…

Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks. However, the adversarial examples generated by many mainstream…