He, Yuhao, Jinyu Tian, Xianwei Zheng, Li Dong, Yuanman Li, and Jiantao Zhou. 2026. “Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (26):21681-89. https://doi.org/10.1609/aaai.v40i26.39318.