Related papers: Prompt-driven Transferable Adversarial Attack on P…

Adversarial example detection plays a vital role in adaptive cyber defense, especially in the face of rapidly evolving attacks. In adaptive cyber defense, the nature and characteristics of attacks continuously change, making it crucial to…

Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of transferable AEs, which succeed across unseen models, is key to…

Vision foundation models are increasingly employed in autonomous driving systems due to their advanced capabilities. However, these models are susceptible to adversarial attacks, posing significant risks to the reliability and safety of…

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's…

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training…

As the AI systems become deeply embedded in social media platforms, we've uncovered a concerning security vulnerability that goes beyond traditional adversarial attacks. It becomes important to assess the risks of LLMs before the general…

Adversarial perturbations can mislead Multimodal Large Language Models (MLLMs) recognize a benign image as a specific target object, posing serious risks in safety-critical scenarios such as autonomous driving and medical diagnosis. This…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Large vision-language models (LVLMs) have demonstrated their incredible capability in image understanding and response generation. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we…

Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual modules introduces new challenges in terms of robustness for…

Transferable adversarial attack has drawn increasing attention due to their practical threaten to real-world applications. In particular, the feature-level adversarial attack is one recent branch that can enhance the transferability via…

As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their susceptibility to adversarial perturbations has emerged as a…

Text attribute person search aims to find specific pedestrians through given textual attributes, which is very meaningful in the scene of searching for designated pedestrians through witness descriptions. The key challenge is the…

The conventional targeted adversarial attacks add a small perturbation to an image to make neural network models estimate the image as a predefined target class, even if it is not the correct target class. Recently, for visual-language…

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of…

Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models,…

Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary…

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…

Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it becomes imperative to assess their adversarial robustness, especially when deploying them in security-crucial…

Vision-language models (VLMs) (e.g. CLIP, LLaVA) are trained on large-scale, lightly curated web datasets, leading them to learn unintended correlations between semantic concepts and unrelated visual signals. These associations degrade…