Off-Distribution Voices: Fanfiction Subgenres as Universal Vernacular Jailbreaks for Aligned LLMs

arXiv:2606.04483v1 Announce Type: new Abstract: Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the real failure mode is not any specific prompt, but an entire register of natural human writing that safety training has under-covered. Building on this insight, we introduce the first jailbreak family that uses real fanfiction subgenres as universal attack carriers: a creative-writing meta 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 no attacker LLM and no per-target adaptation. On eight aligned LLMs over the union of HarmBench and JailbreakBench, this attack lifts mean ASR from 0.278 to 0.731 under a four-judge ensemble; a factorial decomposition shows the gain is carried by register rather than length or structure. Two active defences widen rather than narrow the vernacular-to-baseline ratio, indicating that template-targeting defences merely steer attackers toward register-based attacks like ours. We also propose SAGA-A4, a static four-turn extension that attains mean ASR 0.924, substantially exceeding three existing multi-turn methods.

Abstract:Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the real failure mode is not any specific prompt, but an entire register of natural human writing that safety training has under-covered. Building on this insight, we introduce the first jailbreak family that uses real fanfiction subgenres as universal attack carriers: a creative-writing meta 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 no attacker LLM and no per-target adaptation. On eight aligned LLMs over the union of HarmBench and JailbreakBench, this attack lifts mean ASR from 0.278 to 0.731 under a four-judge ensemble; a factorial decomposition shows the gain is carried by register rather than length or structure. Two active defences widen rather than narrow the vernacular-to-baseline ratio, indicating that template-targeting defences merely steer attackers toward register-based attacks like ours. We also propose SAGA-A4, a static four-turn extension that attains mean ASR 0.924, substantially exceeding three existing multi-turn methods.

Computation and Language (cs.CL)

arXiv:2606.04483 [cs.CL]

(or arXiv:2606.04483v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.04483 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

Off-Distribution Voices: Fanfiction Subgenres as Universal Vernacular Jailbreaks for Aligned LLMs

Subiecte conexe