paperFebruary 2024Unreviewed

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues

Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu

Annual Meeting of the Association for Computational Linguistics

Abstract

With the development of LLMs, the security threats of LLMs are getting more and more attention. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks primarily utilize scenario camouflage techniques. However their explicitly mention of malicious intent will be easily recognized and defended by LLMs. In this paper, we propose an indirect jailbreak attack approach, Puzzler, which can bypass the LLM's defense strategy and obtain malicious re

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@article{chang2024play,
  title = {{Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues}},
  author = {Zhiyuan Chang and Mingyang Li and Yi Liu and Junjie Wang and Qing Wang and Yang Liu},
  year = {2024},
  month = feb,
  journal = {Annual Meeting of the Association for Computational Linguistics},
  eprint = {2402.09091},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2402.09091},
  url = {https://www.semanticscholar.org/paper/490e815b3be11ba97631783d9ae946b8f8517fd6}
}