HE, Yuhao; TIAN, Jinyu; ZHENG, Xianwei; DONG, Li; LI, Yuanman; ZHOU, Jiantao. Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 26, p. 21681–21689, 2026. DOI: 10.1609/aaai.v40i26.39318. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39318. Acesso em: 9 may. 2026.