DARABI, N.; NAIK, D.; TAYEBATI, S.; JAYASURIYA, D.; KRISHNAN, R.; TRIVEDI, A. R. EigenShield: Inference-Time, Model-Agnostic Jailbreaking Defense via Causal Subspace Filtering. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 5, p. 3524-3532, 2026. DOI: 10.1609/aaai.v40i5.37350. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/37350. Acesso em: 5 may. 2026.