相关论文: Vision-LLMs Can Fool Themselves with Self-Generate…

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…

Augmenting Large Language Models (LLMs) with image-understanding capabilities has resulted in a boom of high-performing Vision-Language models (VLMs). While studying the alignment of LLMs to human values has received widespread attention,…

The rapid advancement of Large Language Models (LLMs) presents a significant challenge to academic integrity within computing education. As educators seek reliable detection methods, this paper evaluates the capacity of three prominent LLMs…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be…

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Hallucinations, the generation of apparently convincing yet false statements, remain a major barrier to the safe deployment of LLMs. Building on the strong performance of self-detection methods, we examine the use of structured knowledge…

Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs) into Large Vision-Language Models (LVLMs) for multimodal tasks, but this process often compromises the inherent safety capabilities embedded in the original…

Machine learning based language models have recently made significant progress, which introduces a danger to spread misinformation. To combat this potential danger, several methods have been proposed for detecting text written by these…

Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fragmented, fused, or partially occluded. This paper…

Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge.…

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…

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle…

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities on Visual-Question-Answering (VQA) benchmarks. However, their robustness against textual misinformation remains under-explored. While existing research has…

Recent studies have raised significant concerns regarding the vulnerability of Large Vision Language Models (LVLMs) to maliciously injected or perturbed input images, which can mislead their responses. Existing defense methods show that…

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on…

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

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…

Capabilities of large language models to generate multilingual coherent text have continuously enhanced in recent years, which opens concerns about their potential misuse. Previous research has shown that they can be misused for generation…