Miao Lin, Feng Yu, Rui Ning, Lusi Li, Jiawei Chen, Qian Lou, Mengxin Zheng, Chunsheng Xin, Hongyi Wu. RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance. Trans. Mach. Learn. Res., 2026, 2026. [doi]
Abstract is missing.