Zhao, X. et al. 2026. Good Gradients Poison Your Model: Evading Defenses in Federated Learning via Boundary-adaptive Perturbation. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 16 (Mar. 2026), 13262–13270. DOI:https://doi.org/10.1609/aaai.v40i16.38328.