arXiv SecurityArchived Jun 11, 2026✓ Full text saved
arXiv:2606.11425v1 Announce Type: new Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries. We propose JailbreakOPT, a tool-assisted framework for improving iterative single-turn jailbreak prompt optimization. JailbreakOPT organ
Full text archived locally
✦ AI Summary· Claude Sonnet
Computer Science > Cryptography and Security
[Submitted on 9 Jun 2026]
JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
Ge Shi, Jun Yin, Donglin Xie, Fangyi Liu, Yucan Li, Menglin Liu
Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries. We propose JailbreakOPT, a tool-assisted framework for improving iterative single-turn jailbreak prompt optimization. JailbreakOPT organizes diverse atomic jailbreak prompts into an attack tool library and composes them through a unified intra-episode optimization abstraction to generate stronger standalone attack prompts. To reuse experience across attack episodes, JailbreakOPT further frames tool selection as a contextual bandit problem and applies contextual Thompson sampling to guide exploration and exploitation based on past outcomes. Experiments across multiple target LLMs and attack goals show that JailbreakOPT improves attack success rate (ASR) while reducing the number of attacks until success (No.A) compared with atomic single-turn attacks and existing iterative optimization baselines. This paper may contain offensive or harmful content.
Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.11425 [cs.CR]
(or arXiv:2606.11425v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2606.11425
Focus to learn more
Submission history
From: Ge Shi [view email]
[v1] Tue, 9 Jun 2026 20:22:29 UTC (9,621 KB)
Access Paper:
view license
Current browse context:
cs.CR
< prev | next >
new | recent | 2026-06
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Export BibTeX Citation
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Demos
Related Papers
About arXivLabs
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)