相关论文: VLMs Can Aggregate Scattered Training Patches

Despite emerging efforts to enhance the safety of Vision-Language Models (VLMs), current approaches face two main shortcomings. 1) Existing safety-tuning datasets and benchmarks only partially consider how image-text interactions can yield…

The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language…

Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understudied, raising concerns about amplified misinformation in…

Vision Large Language Models (VLMs) combine visual understanding with natural language processing, enabling tasks like image captioning, visual question answering, and video analysis. While VLMs show impressive capabilities across domains…

Visual-Language Models (VLMs) have become a powerful tool for bridging the gap between visual and linguistic understanding. However, the conventional learning approaches for VLMs often suffer from limitations, such as the high resource…

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,…

Vision-Language Models (VLMs) have emerged as the dominant approach for zero-shot recognition, adept at handling diverse scenarios and significant distribution changes. However, their deployment in risk-sensitive areas requires a deeper…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

Vision-Language Models (VLMs) extend the capabilities of Large Language Models (LLMs) by incorporating visual information, yet they remain vulnerable to jailbreak attacks, especially when processing noisy or corrupted images. Although…

The rapid advancement of Multimodal Large Language Models (MLLMs) has introduced complex security challenges, particularly at the intersection of textual and visual safety. While existing schemes have explored the security vulnerabilities…

Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM backbone. Even blank or irrelevant images can trigger LVLMs…

Medical image segmentation allows quantifying target structure size and shape, aiding in disease diagnosis, prognosis, surgery planning, and comprehension.Building upon recent advancements in foundation Vision-Language Models (VLMs) from…

Large Vision-Language Models (VLMs) are increasingly being regarded as foundation models that can be instructed to solve diverse tasks by prompting, without task-specific training. We examine the seemingly obvious question: how to…

Vision language models (VLMs) are designed to extract relevant visuospatial information from images. Some research suggests that VLMs can exhibit humanlike scene understanding, while other investigations reveal difficulties in their ability…

Large Visual Language Model\textbfs (VLMs) such as GPT-4V have achieved remarkable success in generating comprehensive and nuanced responses. Researchers have proposed various benchmarks for evaluating the capabilities of VLMs. With the…

Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine-tuning with large datasets of input-target pairs. This is a critical bottleneck, as such…

Model inversion (MI) attacks pose significant privacy risks by reconstructing private training data from trained neural networks. While prior studies have primarily examined unimodal deep networks, the vulnerability of vision-language…

Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignment concerns of VLMs have increased significantly due to different categories of attack vectors.…

Large language models (LLMs) have shown great potential as general-purpose AI assistants in various domains. To meet the requirements of different applications, LLMs are often customized by further fine-tuning. However, the powerful…