Zhao X, Shi J, Li Y, Huang J, Fan C. Good Gradients Poison Your Model: Evading Defenses in Federated Learning via Boundary-adaptive Perturbation. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 12];40(16):13262-70. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/38328