相关论文: Document Screenshot Retrievers are Vulnerable to P…

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

Video Large Language Models (VideoLLMs) have emerged as powerful tools for understanding videos, supporting tasks such as summarization, captioning, and question answering. Their performance has been driven by advances in frame sampling,…

While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus on text-image interplay, treating the visual modality as a…

Dense retrievers have achieved state-of-the-art performance in various information retrieval tasks, but their robustness against tokenizer poisoning remains underexplored. In this work, we assess the vulnerability of dense retrieval systems…

Vision-language artificial intelligence models (VLMs) possess medical knowledge and can be employed in healthcare in numerous ways, including as image interpreters, virtual scribes, and general decision support systems. However, here, we…

Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…

Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recognition (OCR) for document search. A recent advance in VDR was…

With over 200 million published academic documents and millions of new documents being written each year, academic researchers face the challenge of searching for information within this vast corpus. However, existing retrieval systems…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating coherent text but remain limited by the static nature of their training data. Retrieval Augmented Generation (RAG) addresses this issue by combining LLMs…

Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external content using the retrieval augmented generation (RAG)…

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic…

Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates that can generate similar images. This work investigates a…

Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images…

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…

Spear-phishing attacks present a significant security challenge, with large language models (LLMs) escalating the threat by generating convincing emails and facilitating target reconnaissance. To address this, we propose a detection…

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…

Recent advances in visual-language alignment have endowed vision-language models (VLMs) with fine-grained image understanding capabilities. However, this progress also introduces new privacy risks. This paper first proposes a novel privacy…

Large-scale image retrieval using deep hashing has become increasingly popular due to the exponential growth of image data and the remarkable feature extraction capabilities of deep neural networks (DNNs). However, deep hashing methods are…

Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first…