相关论文: Are Vision-Language Models Safe in the Wild? A Mem…

Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high…

Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual…

The rapid advancement of pre-trained language models (PLMs) has demonstrated promising results for various code-related tasks. However, their effectiveness in detecting real-world vulnerabilities remains a critical challenge. While existing…

Text-to-Image (T2I) models have made remarkable progress in generating images from text prompts, but their output quality and safety still depend heavily on how prompts are phrased. Existing safety methods typically refine prompts using…

Visually linking matching cues is a crucial ability in daily life, such as identifying the same person in multiple photos based on their cues, even without knowing who they are. Despite the extensive knowledge that vision-language models…

Understanding how effectively large vision language models (VLMs) compare visual inputs is crucial across numerous applications, yet this fundamental capability remains insufficiently assessed. While VLMs are increasingly deployed for tasks…

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…

The emergence of Vision Language Models (VLMs) has brought unprecedented advances in understanding multimodal information. The combination of textual and visual semantics in VLMs is highly complex and diverse, making the safety alignment of…

Multimodal large language models (MLLMs) enable interaction over both text and images, but their safety behavior can be driven by unimodal shortcuts instead of true joint intent understanding. We introduce CSR-Bench, a benchmark for…

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not…

With the rapid development of Large Language Models (LLMs), increasing attention has been paid to their safety concerns. Consequently, evaluating the safety of LLMs has become an essential task for facilitating the broad applications of…

As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of…

The proliferation of multimodal memes in the social media era demands that multimodal Large Language Models (mLLMs) effectively understand meme harmfulness. Existing benchmarks for assessing mLLMs on harmful meme understanding rely on…

Advances in vision language models (VLMs) have enabled the simulation of general human behavior through their reasoning and problem solving capabilities. However, prior research has not investigated such simulation capabilities in the…

Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs) remain largely unexplored. In this paper, we identify emoticon semantic confusion, a vulnerability…

Ensuring the safety of vulnerable road users (VRUs), such as pedestrians and cyclists, is a critical challenge for autonomous driving systems, as crashes involving VRUs often result in severe or fatal consequences. While multimodal large…

Video-Language Models (VLMs) have demonstrated impressive multi-modal reasoning capabilities across diverse computer vision applications. However, these VLMs are task-specific and assume that both video and language inputs are complete.…

Training large language models to follow instructions makes them perform better on a wide range of tasks and generally become more helpful. However, a perfectly helpful model will follow even the most malicious instructions and readily…

Augmented Reality (AR) enhances the real world by integrating virtual content, yet ensuring the quality, usability, and safety of AR experiences presents significant challenges. Could Vision-Language Models (VLMs) offer a solution for the…