Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

2026-05-25

AI Summary

This work addresses the vulnerability of generative models to jailbreaking attacks and the prohibitive cost of comprehensive evaluation. The authors propose a behavioral geometry framework that models the structural relationships among model behaviors, enabling high-accuracy prediction of cross-model jailbreak susceptibility using only a minimal set of probes. By integrating behavioral geometry modeling, vulnerability prediction, and probe optimization, the method achieves an AUPRC of 0.94 across 79 models and 100 configurations while reducing probe usage by 98%. Notably, defense strategies transferred from just three source models outperform provider-matched baselines by 2% (p = 0.03), demonstrating both efficiency and effectiveness in scalable jailbreak mitigation.

Abstract

Evaluating and mitigating a generative system's susceptibility to jailbreak attacks is critical to its safe deployment. Given the number of deployable systems, full per-configuration evaluation and optimization is impractical. In this paper, we formalize the behavioral geometry of a population of models that, by leveraging previously evaluated and defended models, supports both efficient susceptibility prediction and effective defense transfer across a population. We apply the framework to 79 models spanning 24 providers and to 100 system configurations of a single base model. Simple methods that use the behavioral geometry reach an AUPRC of $0.94$ for susceptibility detection with $\approx98\%$ fewer probes relative to a full evaluation. Using the behavioral geometry to select which model to transfer an optimized defense from outperforms same-provider assignment ($+2\%$, $p = 0.03$) at no additional probe cost, with a set of three models sufficient to cover the population. Results are robust to hyperparameter selection and judge.

Problem

• jailbreak susceptibility
• generative models
• behavioral geometry
• defense transfer
• model evaluation

Innovation

• behavioral geometry
• jailbreak susceptibility
• defense transfer
• efficient evaluation
• model population