中文
相关论文

相关论文: Every Picture Tells a Dangerous Story: Memory-Augm…

200 篇论文

Jailbreak attacks on large language models (LLMs) aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is especially important for safety evaluation, where the attacker observes…

密码学与安全 · 计算机科学 2026-05-29 Junke Zhang , Jianwei Wang , Sishuo Chen , Yizhang He , Qingshuai Feng , Zhengyi Yang

Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside…

密码学与安全 · 计算机科学 2026-04-24 Rui Yang Tan , Yujia Hu , Roy Ka-Wei Lee

Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak attacks often inject malicious instructions from text into…

机器学习 · 计算机科学 2025-05-23 Zhaoxin Wang , Handing Wang , Cong Tian , Yaochu Jin

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Ruofan Wang , Xingjun Ma , Hanxu Zhou , Chuanjun Ji , Guangnan Ye , Yu-Gang Jiang

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

密码学与安全 · 计算机科学 2025-07-18 Yi Nian , Shenzhe Zhu , Yuehan Qin , Li Li , Ziyi Wang , Chaowei Xiao , Yue Zhao

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

Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bring more vulnerabilities to being utilized for jailbreak…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Shiji Zhao , Shukun Xiong , Yao Huang , Yan Jin , Zhenyu Wu , Jiyang Guan , Ranjie Duan , Jialing Tao , Hui Xue , Xingxing Wei

With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), ensuring their safety has become increasingly critical. To achieve this objective, it requires us to proactively discover the vulnerability of MLLMs by…

密码学与安全 · 计算机科学 2024-06-13 Siyuan Ma , Weidi Luo , Yu Wang , Xiaogeng Liu

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.…

密码学与安全 · 计算机科学 2025-10-14 Aofan Liu , Lulu Tang

Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…

密码学与安全 · 计算机科学 2026-02-12 Yu Yan , Sheng Sun , Shengjia Cheng , Teli Liu , Mingfeng Li , Min Liu

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

密码学与安全 · 计算机科学 2023-10-12 Erfan Shayegani , Yue Dong , Nael Abu-Ghazaleh

Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure deployment. Previous studies have shown that introducing…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Yilian Liu , Xiaojun Jia , Guoshun Nan , Jiuyang Lyu , Zhican Chen , Tao Guan , Shuyuan Luo , Zhongyi Zhai , Yang Liu

Multimodal Large Language Models (MLLMs), which integrate vision and other modalities into Large Language Models (LLMs), significantly enhance AI capabilities but also introduce new security vulnerabilities. By exploiting the…

密码学与安全 · 计算机科学 2025-10-10 Aofan Liu , Lulu Tang , Ting Pan , Yuguo Yin , Bin Wang , Ao Yang

Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual inputs. However, despite recent advances in safety alignment, MLLMs remain vulnerable to…

密码学与安全 · 计算机科学 2026-03-10 Xinkai Wang , Beibei Li , Zerui Shao , Ao Liu , Guangquan Xu , Shouling Ji

This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries. A maximum likelihood-based algorithm is proposed to find an…

机器学习 · 计算机科学 2024-02-07 Zhenxing Niu , Haodong Ren , Xinbo Gao , Gang Hua , Rong Jin

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

密码学与安全 · 计算机科学 2025-08-14 Boyuan Chen , Minghao Shao , Abdul Basit , Siddharth Garg , Muhammad Shafique

As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real-world tasks. However, MLLMs face significant security…

密码学与安全 · 计算机科学 2024-10-23 Fenghua Weng , Yue Xu , Chengyan Fu , Wenjie Wang

With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted…

计算机视觉与模式识别 · 计算机科学 2025-06-19 Yu Wang , Xiaofei Zhou , Yichen Wang , Geyuan Zhang , Tianxing He

With the emergence of strong vision language capabilities, multimodal large language models (MLLMs) have demonstrated tremendous potential for real-world applications. However, the security vulnerabilities exhibited by the visual modality…

计算机视觉与模式识别 · 计算机科学 2025-09-17 Ziqi Miao , Yi Ding , Lijun Li , Jing Shao

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
‹ 上一页 1 2 3 10 下一页 ›