Behavioral geometry of model populations enables high-accuracy jailbreak susceptibility prediction and defense transfer with 98% fewer evaluations.
Trosset and Carey E
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
Behavioral geometry of model populations enables high-accuracy jailbreak susceptibility prediction and defense transfer with 98% fewer evaluations.