Interpretability Derived Backdoor Attacks Detection in Deep Neural Networks: Work-in-Progress

Xiangyu Wen, Wei Jiang 0016, Jinyu Zhan, Xupeng Wang, Zhiyuan He. Interpretability Derived Backdoor Attacks Detection in Deep Neural Networks: Work-in-Progress. In Tulika Mitra, Andreas Gerstlauer, editors, 20th International Conference on Embedded Software, EMSOFT 2020, Singapore, September 20-25, 2020. pages 13-14, IEEE, 2020. [doi]

Abstract

Abstract is missing.