New Wide-Net-Casting Jailbreak Attacks Risk Large Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910228271857664 |
|---|---|
| author | Xiang, Qiuchi Qu, Haoxuan Rahmani, Hossein Liu, Jun |
| author_facet | Xiang, Qiuchi Qu, Haoxuan Rahmani, Hossein Liu, Jun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17128 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | New Wide-Net-Casting Jailbreak Attacks Risk Large Models Xiang, Qiuchi Qu, Haoxuan Rahmani, Hossein Liu, Jun Cryptography and Security Artificial Intelligence 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. |
| title | New Wide-Net-Casting Jailbreak Attacks Risk Large Models |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2605.17128 |