1. DeepFace: Closing the Gap to Human-Level Performance in Face Verification
2. Certified defenses for data poisoning attacks;steinhardt;NeurIPS,2017
3. Certified robustness to label-flipping attacks via randomized smoothing;rosenfeld;In ICML,2020
4. Trojanzoo: Ev-erything you ever wanted to know about neural backdoors (but were afraid to ask);pang;ArXiv Preprint,2020
5. Wanet-imperceptible warping-based backdoor attack;nguyen;In ICLR,2020