New Wide-Net-Casting Jailbreak Attacks Risk Large Models

Computer Science > Cryptography and Security [Submitted on 16 May 2026] New Wide-Net-Casting Jailbreak Attacks Risk Large Models Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani, Jun Liu Jailbreak attacks on large models have drawn growing attention due to their close ties to societal safety. This work identifies a practical yet unexplored jailbreak scenario, the wide-net-casting scenario, where an adversary can query a group of large models instead of a single one to elicit harmful outputs. Our analysis reveals substantial yet previously overlooked safety risks under this scenario. As a key part of our analysis, we further develop a novel jailbreak method tailored to the wide-net-casting scenario. With this tailored method, the jailbreak success rate can even reach 100\% in some experiments when targeting the large models without additional safeguards, exposing wide-net-casting as a distinct, high-risk scenario that warrants attention in future evaluation and defense research. Comments: Accepted at ICML 2026; project page at this https URL Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2605.17128 [cs.CR]   (or arXiv:2605.17128v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.17128 Focus to learn more Submission history From: Qiuchi Xiang [view email] [v1] Sat, 16 May 2026 19:22:54 UTC (8,715 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 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?)