相关论文: Improving Adversarial Transferability of Vision-La…

With the emergence of more powerful large language models (LLMs), such as ChatGPT and GPT-4, in-context learning (ICL) has gained significant prominence in leveraging these models for specific tasks by utilizing data-label pairs as…

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces. Despite their effectiveness, these models remain vulnerable…

Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images…

Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model…

Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce hallucinations, manipulate responses, or bypass safety mechanisms. Existing methods seek to…

Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…

Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal…

The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial…

Large Vision-Language Models (VLMs) have revolutionized computer vision, enabling tasks such as image classification, captioning, and visual question answering. However, they remain highly vulnerable to adversarial attacks, particularly in…

Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared (VIS-IR) scenarios remains underexplored. This gap is critical because VIS-IR sensing is…

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…

In recent years, despite significant advancements in adversarial attack research, the security challenges in cross-modal scenarios, such as the transferability of adversarial attacks between infrared, thermal, and RGB images, have been…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on…

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents,…

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…

Person re-identification (re-id) models are vital in security surveillance systems, requiring transferable adversarial attacks to explore the vulnerabilities of them. Recently, vision-language models (VLM) based attacks have shown superior…

Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal…

Transferable adversarial examples are known to cause threats in practical, black-box attack scenarios. A notable approach to improving transferability is using integrated gradients (IG), originally developed for model interpretability. In…