← 研踪 PaperTrailarXiv:2605.26409 · v2
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
首次提交 2026-05-26 08:36
版本更新 2026-11-06 04:10
雷达观测 2026-11-09 10:16
摘要
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 82 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 ($+4.1\%$, $p = 0.004$) at no additional probe cost, with a set of three models sufficient to cover the population. Results are robust to hyperparameter selection and judge.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-06 04:10 · 最新观测版本
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models
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 82 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 ($+4.1\%$, $p = 0.004$) at no additional probe cost, with a set of three models sufficient to cover the population. Results are robust to hyperparameter selection and judge.
查看此版本解读 →查看此版本原文 ↗