New Wide-Net-Casting Jailbreak Attacks Risk Large Models
摘要
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.
引用
@article{arxiv.2605.17128,
title = {New Wide-Net-Casting Jailbreak Attacks Risk Large Models},
author = {Qiuchi Xiang and Haoxuan Qu and Hossein Rahmani and Jun Liu},
journal= {arXiv preprint arXiv:2605.17128},
year = {2026}
}
备注
Accepted at ICML 2026; project page at https://zzlz233.github.io/Wide-net-casting/