Giarrusso, F., Sorokoletova, O., Suriani, V., & Nardi, D. (2026). Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection. Proceedings of IASEAI Conference, 2(1), 191–203. Retrieved from https://ojs.aaai.org/index.php/IASEAI/article/view/43024