中文
相关论文

相关论文: Eyes Closed, Safety On: Protecting Multimodal LLMs…

200 篇论文

Attracted by the impressive power of Multimodal Large Language Models (MLLMs), the public is increasingly utilizing them to improve the efficiency of daily work. Nonetheless, the vulnerabilities of MLLMs to unsafe instructions bring huge…

计算机视觉与模式识别 · 计算机科学 2024-06-21 Xin Liu , Yichen Zhu , Yunshi Lan , Chao Yang , Yu Qiao

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…

密码学与安全 · 计算机科学 2024-06-18 Renjie Pi , Tianyang Han , Jianshu Zhang , Yueqi Xie , Rui Pan , Qing Lian , Hanze Dong , Jipeng Zhang , Tong Zhang

Large visual-language models (LVLMs) integrate aligned large language models (LLMs) with visual modules to process multimodal inputs. However, the safety mechanisms developed for text-based LLMs do not naturally extend to visual modalities,…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Shen Li , Liuyi Yao , Wujia Niu , Lan Zhang , Yaliang Li

Multi-modal large language models (MLLMs), capable of processing text, images, and audio, have been widely adopted in various AI applications. However, recent MLLMs integrating images and text remain highly vulnerable to coordinated…

密码学与安全 · 计算机科学 2025-12-19 Zihao Wang , Kar Wai Fok , Vrizlynn L. L. Thing

The deployment of multimodal large language models (MLLMs) has demonstrated remarkable success in engaging in conversations involving visual inputs, thanks to the superior power of large language models (LLMs). Those MLLMs are typically…

计算与语言 · 计算机科学 2024-10-10 Jiahui Gao , Renjie Pi , Tianyang Han , Han Wu , Lanqing Hong , Lingpeng Kong , Xin Jiang , Zhenguo Li

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Zhendong Liu , Yuanbi Nie , Yingshui Tan , Xiangyu Yue , Qiushi Cui , Chongjun Wang , Xiaoyong Zhu , Bo Zheng

Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer from two key limitations: (1) They solely focus on textual…

密码学与安全 · 计算机科学 2025-03-17 Shuyang Hao , Yiwei Wang , Bryan Hooi , Ming-Hsuan Yang , Jun Liu , Chengcheng Tang , Zi Huang , Yujun Cai

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…

计算机视觉与模式识别 · 计算机科学 2024-06-21 Xin Liu , Yichen Zhu , Jindong Gu , Yunshi Lan , Chao Yang , Yu Qiao

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

人工智能 · 计算机科学 2026-05-13 Xinyi Zeng , Xue Yang , Jingyuan Zhang , Huanqian Yan , Xiang Chen , Kaiwen Wei , Hankun Kang , Yu Tian

Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to…

密码学与安全 · 计算机科学 2025-10-27 Xingwei Zhong , Kar Wai Fok , Vrizlynn L. L. Thing

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

人工智能 · 计算机科学 2025-11-04 Yifan Xia , Guorui Chen , Wenqian Yu , Zhijiang Li , Philip Torr , Jindong Gu

Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks…

密码学与安全 · 计算机科学 2025-10-24 Divyanshu Kumar , Shreyas Jena , Nitin Aravind Birur , Tanay Baswa , Sahil Agarwal , Prashanth Harshangi

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

密码学与安全 · 计算机科学 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…

密码学与安全 · 计算机科学 2025-06-03 Youze Wang , Wenbo Hu , Yinpeng Dong , Jing Liu , Hanwang Zhang , Richang Hong

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…

计算与语言 · 计算机科学 2025-06-23 Lei Jiang , Zixun Zhang , Zizhou Wang , Xiaobing Sun , Zhen Li , Liangli Zhen , Xiaohua Xu

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Ce Zhang , Jinxi He , Junyi He , Katia Sycara , Yaqi Xie

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…

密码学与安全 · 计算机科学 2024-11-11 Pete Janowczyk , Linda Laurier , Ave Giulietta , Arlo Octavia , Meade Cleti

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence…

机器学习 · 计算机科学 2024-06-19 Yongshuo Zong , Ondrej Bohdal , Tingyang Yu , Yongxin Yang , Timothy Hospedales
‹ 上一页 1 2 3 10 下一页 ›