English
Related papers

Related papers: DUAL-Bench: Measuring Over-Refusal and Robustness …

200 papers

Multimodal Large Language Models (MLLMs), are recent advancement of Vision-Language Models (VLMs) that have driven major advances in video understanding. However, their vulnerability to adversarial tampering and manipulations remains…

The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Xin Liu , Yichen Zhu , Jindong Gu , Yunshi Lan , Chao Yang , Yu Qiao

Safety concerns of Multimodal large language models (MLLMs) have gradually become an important problem in various applications. Surprisingly, previous works indicate a counterintuitive phenomenon that using textual unlearning to align MLLMs…

Cryptography and Security · Computer Science 2025-05-20 Xuhao Hu , Dongrui Liu , Hao Li , Xuanjing Huang , Jing Shao

Object level hallucination remains a central reliability challenge for vision language models (VLMs), particularly in binary object existence verification. Existing benchmarks emphasize aggregate accuracy but rarely disentangle whether…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 JiYang Wang , Jiawei Chen , Mengqi Xiao , Yu Cheng , Yangfu Li , Zhaoxia Yin

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Qishun Yang , Shu Yang , Lijie Hu , Di Wang

Vision-Language Models (VLMs) show great promise for autonomous driving, but their suitability for safety-critical scenarios is largely unexplored, raising safety concerns. This issue arises from the lack of comprehensive benchmarks that…

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…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Muhammad Adil , Gaang Lee , Vicente A. Gonzalez , Qipei Mei

Large Vision-Language Models (LVLMs) have made significant strides in the field of video understanding in recent times. Nevertheless, existing video benchmarks predominantly rely on text prompts for evaluation, which often require complex…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Yiming Zhao , Yu Zeng , Yukun Qi , YaoYang Liu , Xikun Bao , Lin Chen , Zehui Chen , Qing Miao , Chenxi Liu , Jie Zhao , Feng Zhao

Vision-language models (VLMs) have made significant progress in recent visual-question-answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However, are these models truly effective? In this work, we show that VLMs…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Baiqi Li , Zhiqiu Lin , Wenxuan Peng , Jean de Dieu Nyandwi , Daniel Jiang , Zixian Ma , Simran Khanuja , Ranjay Krishna , Graham Neubig , Deva Ramanan

Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various…

Cryptography and Security · Computer Science 2025-07-16 Yiting Qu , Michael Backes , Yang Zhang

Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to prevent harmful outputs, they often lead to overly cautious…

Machine Learning · Computer Science 2025-10-28 Ziheng Cheng , Yixiao Huang , Hui Xu , Somayeh Sojoudi , Xuandong Zhao , Dawn Song , Song Mei

Safety evaluations of language models often treat serving configuration as fixed background infrastructure, but batch condition is an untested treatment variable whenever the same prompt may be evaluated alone, in a synchronized batch, or…

Machine Learning · Computer Science 2026-05-28 Sahil Kadadekar

As safety remains a crucial concern throughout the development lifecycle of Large Language Models (LLMs), researchers and industrial practitioners have increasingly focused on safeguarding and aligning LLM behaviors with human preferences…

Computation and Language · Computer Science 2024-07-11 Jiayang Song , Yuheng Huang , Zhehua Zhou , Lei Ma

Current benchmarks for assessing vision-language models (VLMs) often focus on their perception or problem-solving capabilities and neglect other critical aspects such as fairness, multilinguality, or toxicity. Furthermore, they differ in…

Computer Vision and Pattern Recognition · Computer Science 2024-10-25 Tony Lee , Haoqin Tu , Chi Heem Wong , Wenhao Zheng , Yiyang Zhou , Yifan Mai , Josselin Somerville Roberts , Michihiro Yasunaga , Huaxiu Yao , Cihang Xie , Percy Liang

Vision Large Language Models (VLLMs) have demonstrated impressive capabilities in general visual tasks such as image captioning and visual question answering. However, their effectiveness in specialized, safety-critical domains like…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Tong Zeng , Longfeng Wu , Liang Shi , Dawei Zhou , Feng Guo

Vision Language Models (VLMs) extend remarkable capabilities of text-only large language models and vision-only models, and are able to learn from and process multi-modal vision-text input. While modern VLMs perform well on a number of…

Computation and Language · Computer Science 2025-07-22 Hannah Sterz , Jonas Pfeiffer , Ivan Vulić

Rapid deployment of vision-language models (VLMs) magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate…

Computation and Language · Computer Science 2025-09-24 DongGeon Lee , Joonwon Jang , Jihae Jeong , Hwanjo Yu

Vision-Language Models (VLMs) have shown capabilities in interpreting visual content, but their reliability in safety-critical scenarios remains insufficiently explored. We introduce VERI, a diagnostic benchmark comprising 200 synthetic…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Dasol Choi , Seunghyun Lee , Youngsook Song

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Cryptography and Security · Computer Science 2026-04-03 Nanxi Li , Zhengyue Zhao , G. Edward Suh , Marco Pavone , Chaowei Xiao

Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstrates that advanced Multimodal Large Language Models (MLLMs)…

Computation and Language · Computer Science 2024-06-27 Xirui Li , Hengguang Zhou , Ruochen Wang , Tianyi Zhou , Minhao Cheng , Cho-Jui Hsieh