Images are Achilles’ Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

被引：0
|
作者：
Li, Yifan [1 ,3 ]
Guo, Hangyu [1 ,3 ]
Zhou, Kun [2 ,3 ]
Zhao, Wayne Xin [1 ,3 ]
Wen, Ji-Rong [1 ,2 ,3 ]
机构：
[1] Gaoling School of Artificial Intelligence, Renmin University of China, China
[2] School of Information, Renmin University of China, China
[3] Beijing Key Laboratory of Big Data Management and Analysis Methods, China
来源：
arXiv |
关键词：
Compilation and indexing terms; Copyright 2025 Elsevier Inc;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Alignment - Problem oriented languages
引用
收藏
相关论文
共 50 条
  • [1] Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models
    Yang, Hao
    Qu, Lizhen
    Shareghi, Ehsan
    Haffari, Gholamreza
    arXiv,
  • [2] Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
    Hao, Shuyang
    Hooi, Bryan
    Liu, Jun
    Chang, Kai-Wei
    Huang, Zi
    Cai, Yujun
    arXiv,
  • [3] Visual cognition in multimodal large language models
    Luca M. Schulze Buschoff
    Elif Akata
    Matthias Bethge
    Eric Schulz
    Nature Machine Intelligence, 2025, 7 (1) : 96 - 106
  • [4] EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
    Zhou, Weikang
    Wang, Xiao
    Xiong, Limao
    Xia, Han
    Gu, Yingshuang
    Chai, Mingxu
    Zhu, Fukang
    Huang, Caishuang
    Dou, Shihan
    Xi, Zhiheng
    Zheng, Rui
    Gao, Songyang
    Zou, Yicheng
    Yan, Hang
    Le, Yifan
    Wang, Ruohui
    Li, Lijun
    Shao, Jing
    Gui, Tao
    Zhang, Qi
    Huang, Xuanjing
    arXiv,
  • [5] Jailbreaking Black Box Large Language Models in Twenty Queries
    Chao, Patrick
    Robey, Alexander
    Dobriban, Edgar
    Hassani, Hamed
    Pappas, George J.
    Wong, Eric
    arXiv, 2023,
  • [6] Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
    Zhao, Wei
    Li, Zhe
    Li, Yige
    Sun, Jun
    arXiv,
  • [7] Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
    Jia, Xiaojun
    Pang, Tianyu
    Du, Chao
    Huang, Yihao
    Gu, Jindong
    Liu, Yang
    Cao, Xiaochun
    Lin, Min
    arXiv,
  • [8] JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
    Jin, Haibo
    Hu, Leyang
    Li, Xinnuo
    Zhang, Peiyan
    Chen, Chonghan
    Zhuang, Jun
    Wang, Haohan
    arXiv,
  • [9] Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
    Xu, Nan
    Wang, Fei
    Zhou, Ben
    Li, Bangzheng
    Xiao, Chaowei
    Chen, Muhao
    Findings of the Association for Computational Linguistics: NAACL 2024 - Findings, 2024, : 3526 - 3548
  • [10] The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
    School of Computer Science and Technology, Xidian University, China
    arXiv,
12345