Voices Across Registers: Corpus-Conditioned Vernacular Jailbreaks against Aligned LLMs via Fanfiction Subgenres
Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the broader failure mode may lie not in any specific prompt, but in natural writing registers that safety tuning under-covers. Building on this insight, we introduce VAR, the first jailbreak family that uses real fanfiction subgenres as universal attack carriers: a creative-writing meta prompt is conditioned on passages from one of twelve Archive of Our Own (AO3) subgenres, and the harmful behavior is embedded as the climax of the resulting scene. The construction requires neither an adversarial attacker LLM nor optimization. On eight aligned LLMs over the u...
| Authors | Zhongze Luo, Ruihe Shi, Zhenshuai Yin et al. |
|---|---|
| Primary category | cs.CL |
| Published | 3 June 2026 |
| Last updated at source | 30 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.