no code implementations • NeurIPS 2018 • Zhi-Hao Zheng, Pengyu Hong
Our approach tries to capture the intrinsic properties of a DNN classifier and uses them to detect adversarial inputs.
no code implementations • ROCLINGIJCLCLP 2016 • Xu-Xiang Wang, Zhi-Hao Zheng, Yu Tsao, Jhih-Wei Hong
Speech Enhancement