Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache

Computer Science > Cryptography and Security [Submitted on 12 Mar 2026] Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache Xinhai Wang, Shaopeng Fu, Shu Yang, Liangyu Wang, Tianhang Zheng, Di Wang Suffix jailbreak attacks serve as a systematic method for red-teaming Large Language Models (LLMs) but suffer from prohibitive computational costs, as a large number of candidate suffixes need to be evaluated before identifying a jailbreak suffix. This paper presents Prefix-Shared KV Cache (PSKV), a plug-and-play inference optimization technique tailored for jailbreak suffix generation. Our method is motivated by a key observation that when performing suffix jailbreaking, while a large number of candidate prompts need to be evaluated, they share the same targeted harmful instruction as the prefix. Therefore, instead of performing redundant inference on the duplicated prefix, PSKV maintains a single KV cache for this prefix and shares it with every candidate prompt, enabling the parallel inference of diverse suffixes with minimal memory overhead. This design enables more aggressive batching strategies that would otherwise be limited by memory constraints. Extensive experiments on six widely used suffix attacks across five widely deployed LLMs demonstrate that PSKV reduces inference time by 40\% and peak memory usage by 50\%, while maintaining the original Attack Success Rate (ASR). The code has been submitted and will be released publicly. Comments: 15 pages, 3 figures, preprint Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) MSC classes: 68T07 ACM classes: I.2.7 Cite as: arXiv:2603.13420 [cs.CR]   (or arXiv:2603.13420v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.13420 Focus to learn more Submission history From: Xinhai Wang [view email] [v1] Thu, 12 Mar 2026 21:07:20 UTC (688 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 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?)