Jailbreak Distillation generates candidate jailbreak prompts on small development models and selects the most effective subset, producing safety benchmarks that transfer to a wide range of held-out models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Jailbreak Distillation: Renewable Safety Benchmarking
Jailbreak Distillation generates candidate jailbreak prompts on small development models and selects the most effective subset, producing safety benchmarks that transfer to a wide range of held-out models.