Fanfiction subgenres from AO3 function as universal register-based jailbreaks, raising mean attack success rate from 0.278 to 0.731 across eight aligned LLMs on HarmBench and JailbreakBench.
Advances in Neural Information Processing Systems , volume =
3 Pith papers cite this work, alongside 21 external citations. Polarity classification is still indexing.
3
Pith papers citing it
21
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
PRISM detects and stops credential leakage during LLM generation in multi-agent pipelines using per-token risk scores from lexical, structural, and behavioral signals, achieving zero observed leaks and F1 of 0.832 on a 2000-task benchmark.
citing papers explorer
-
Off-Distribution Voices: Fanfiction Subgenres as Universal Vernacular Jailbreaks for Aligned LLMs
Fanfiction subgenres from AO3 function as universal register-based jailbreaks, raising mean attack success rate from 0.278 to 0.731 across eight aligned LLMs on HarmBench and JailbreakBench.
-
PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM Pipelines
PRISM detects and stops credential leakage during LLM generation in multi-agent pipelines using per-token risk scores from lexical, structural, and behavioral signals, achieving zero observed leaks and F1 of 0.832 on a 2000-task benchmark.
- Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs