MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the EdgeGeng YuanXialong Maet al.2021NeurIPS 2021
Towards query-efficient black-box adversary with zeroth-order natural gradient descentPu ZhaoPin-Yu Chenet al.2020AAAI 2020
AdvMS: A Multi-Source Multi-Cost Defense Against Adversarial AttacksXiao WangSiyue Wanget al.2020ICASSP 2020
Protecting neural networks with hierarchical random switching: Towards better robustness-accuracy trade-off for stochastic defensesXiao WangSiyue Wanget al.2019IJCAI 2019