11573/1776031 - 2026 -
Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection Giarrusso, F.; Sorokoletova, O.; Suriani, V.; Nardi, Daniele. - 04b Atto di convegno in volume
conference: Second International Association for Safe and Ethical AI Conference (IASEAI'26) (Paris; France)
book: Proceedings of the 2nd IASEAI Conference (IASEAI'26) - (9781577359159)
11573/1776121 - 2026 -
Learning from Mistakes: Can LLM Self-Recover after Misalignment? Sorokoletova, O.; Giarrusso, F.; Suriani, V.; Nardi, D. - 04b Atto di convegno in volume
conference: 2026 Machine Ethics: From Formal Methods to Emergent Machine Ethics Workshop, MEW 2026 (Singapore)
book: MEW 2026 Machine Ethics: from formal methods to emergent machine ethics 2026 - ()