Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking

被引：0
|
作者：
Xu, Nan [1 ]
Wang, Fei [1 ]
Zhou, Ben [2 ]
Li, Bangzheng [1 ]
Xiao, Chaowei [3 ]
Chen, Muhao [4 ]
机构：
[1] University of Southern California, United States
[2] University of Pennsylvania, United States
[3] University of Wisconsin Madison, United States
[4] University of California, Davis, United States
来源：
Findings of the Association for Computational Linguistics: NAACL 2024 - Findings | 2024年
关键词：
Compendex;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Computational linguistics
引用
收藏
页码：3526 / 3548
相关论文
共 50 条
  • [1] 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,
  • [2] Jailbreaking Black Box Large Language Models in Twenty Queries
    Chao, Patrick
    Robey, Alexander
    Dobriban, Edgar
    Hassani, Hamed
    Pappas, George J.
    Wong, Eric
    arXiv, 2023,
  • [3] Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
    Zhao, Wei
    Li, Zhe
    Li, Yige
    Sun, Jun
    arXiv,
  • [4] 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,
  • [5] The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
    School of Computer Science and Technology, Xidian University, China
    arXiv,
  • [6] 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,
  • [7] Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology
    National University of Defense Technology, China
    不详
    arXiv,
  • [8] Open Sesame! Universal Black-Box Jailbreaking of Large Language Models
    Lapid, Raz
    Langberg, Ron
    Sipper, Moshe
    APPLIED SCIENCES-BASEL, 2024, 14 (16):
  • [9] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
    Zhang, Zhexin
    Yang, Junxiao
    Ke, Pei
    Mi, Fei
    Wang, Hongning
    Huang, Minlie
    PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, : 8865 - 8887
  • [10] Jailbreaking Pre-trained Large Language Models Towards Hardware Vulnerability Insertion Ability
    Wan, Gwok-Waa
    Wong, Sam-Zaak
    Wang, Xi
    PROCEEDING OF THE GREAT LAKES SYMPOSIUM ON VLSI 2024, GLSVLSI 2024, 2024, : 579 - 582
12345