#jailbreakdetection — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #jailbreakdetection, aggregated by home.social.
-
This paper introduces a model-agnostic threat evaluation using N-gram language models to measure jailbreak likelihood, finding discrete optimization attacks more effective than LLM-based ones and that jailbreaks often exploit rare bigrams.
Read more: https://arxiv.org/abs/2410.16222
-
This paper introduces a model-agnostic threat evaluation using N-gram language models to measure jailbreak likelihood, finding discrete optimization attacks more effective than LLM-based ones and that jailbreaks often exploit rare bigrams.
Read more: https://arxiv.org/abs/2410.16222