Giarrusso, Francesco, Olga Sorokoletova, Vincenzo Suriani, and Daniele Nardi. “Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection”. Proceedings of IASEAI Conference 2, no. 1 (July 15, 2026): 191–203. Accessed July 15, 2026. https://ojs.aaai.org/index.php/IASEAI/article/view/43024.