Interpretability-Guided Defense Against Backdoor Attacks to Deep Neural Networks

Wei Jiang 0016, Xiangyu Wen, Jinyu Zhan, Xupeng Wang, Ziwei Song. Interpretability-Guided Defense Against Backdoor Attacks to Deep Neural Networks. IEEE Trans. on CAD of Integrated Circuits and Systems, 41(8):2611-2624, 2022. [doi]

Abstract

Abstract is missing.