Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

Computer Science > Cryptography and Security [Submitted on 26 May 2026] Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Hayden Helm, Xiaodong Liu, Weiwei Yang 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. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2605.26409 [cs.CR]   (or arXiv:2605.26409v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.26409 Focus to learn more Submission history From: Hayden Helm [view email] [v1] Tue, 26 May 2026 00:36:42 UTC (319 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)