No tested defense, including the paper's own transcript classifier, can fully stop an LLM from giving competent bomb-making instructions under a grey-box attacker.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach
No tested defense, including the paper's own transcript classifier, can fully stop an LLM from giving competent bomb-making instructions under a grey-box attacker.