CUI, J.; HAN, Y.; JIAO, J.; ZHANG, J. Persistent Backdoor Attacks Under Continual Fine-Tuning of LLMs. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 36, p. 30422-30430, 2026. DOI: 10.1609/aaai.v40i36.40295. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40295. Acesso em: 30 apr. 2026.