Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
Preprint
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 response by implicitly providing LLMs with some clues about the original malicious query. In addition, inspired by the wisdom of "When unable to attack, defend" from Sun Tzu's Art of War, we adopt a defensive stance to gather clues about the original malicious query through LLMs. Extensive experimental results show that Puzzler achieves a query success rate of 96.6% on closed-source LLMs, which is 57.9%-82.7% higher than baselines. Furthermore, when tested against the state-of-the-art jailbreak detection approaches, Puzzler proves to be more effective at evading detection compared to baselines.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- Software Testing With Large Language Models: Survey, Landscape, and VisionIEEE Transactions on Software Engineering, 2024
- Tree of Attacks: Jailbreaking Black-Box LLMs Automatically2024
- PANDORA: Jailbreak GPTs by Retrieval Augmented Generation Poisoning2024
- InFoBench: Evaluating Instruction Following Ability in Large Language Models2024
- A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily2024