He, Yuhao, Jinyu Tian, Xianwei Zheng, Li Dong, Yuanman Li, and Jiantao Zhou. “Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 26 (March 14, 2026): 21681–21689. Accessed May 9, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/39318.