New Wide-Net-Casting Jailbreak Attacks Risk Large Models

Abstract

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-n

Categories

Framework mappings

Suggested from the entry's categories.

@misc{xiang2026new,
  title = {{New Wide-Net-Casting Jailbreak Attacks Risk Large Models}},
  author = {Qiuchi Xiang and Haoxuan Qu and Hossein Rahmani and Jun Liu},
  year = {2026},
  month = may,
  eprint = {2605.17128},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.17128}
}