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

Meme-based social abuse detection is challenging because harmful intent often relies on implicit cultural symbolism and subtle cross-modal incongruence. Prior approaches, from fusion-based methods to in-context learning with Large…

Safety hazard identification and prevention are the key elements of proactive safety management. Previous research has extensively explored the applications of computer vision to automatically identify hazards from image clips collected…

There has been an increasing interest in the alignment of large language models (LLMs) with human values. However, the safety issues of their integration with a vision module, or vision language models (VLMs), remain relatively…

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…

We propose GuessBench, a novel benchmark that evaluates Vision Language Models (VLMs) on modeling the pervasive, noisy, and pluralistic human creativity. GuessBench sources data from "Guess the Build", an online multiplayer Minecraft…

Vision-Language Models (VLMs) trained on web-scale corpora excel at natural image tasks and are increasingly repurposed for healthcare; however, their competence in medical tasks remains underexplored. We present a comprehensive evaluation…

Memes on the Internet are often harmless and sometimes amusing. However, by using certain types of images, text, or combinations of both, the seemingly harmless meme becomes a multimodal type of hate speech -- a hateful meme. The Hateful…

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

The automatic identification of harmful content online is of major concern for social media platforms, policymakers, and society. Researchers have studied textual, visual, and audio content, but typically in isolation. Yet, harmful content…

Memes are a popular element of modern web communication, used not only as static artifacts but also as interactive replies within conversations. While computational research has focused on analyzing the intrinsic properties of memes, the…

Embodied agents can identify and report safety hazards in the home environments. Accurately evaluating their capabilities in home safety inspection tasks is curcial, but existing benchmarks suffer from two key limitations. First, they…

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.…

This paper introduces a novel benchmark dataset designed to evaluate the capabilities of Vision Language Models (VLMs) on tasks that combine visual reasoning with subject-specific background knowledge in the German language. In contrast to…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to LLMs form Vision Language Models (VLMs). However, recent research shows that the visual modality in VLMs is highly…

With the rapid advancement of Large Vision-Language Models (LVLMs), ensuring their safety has emerged as a crucial area of research. This survey provides a comprehensive analysis of LVLM safety, covering key aspects such as attacks,…

As large language models (LLMs) develop increasingly sophisticated capabilities and find applications in medical settings, it becomes important to assess their medical safety due to their far-reaching implications for personal and public…

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in…

Recent Vision-Language Models (VLMs) have made remarkable progress in multimodal understanding tasks, yet their evaluation on long video understanding remains unreliable. Due to limited frame inputs, key frames necessary for answering the…

One way to mitigate risks in vision-language models (VLMs) is to remove dangerous samples in their training data. However, such data moderation can be easily bypassed when harmful images are split into small, benign-looking patches,…