Understanding adversarial robustness via critical attacking route

• Main Authors: LI, Tianlin, LIU, Aishan, LIU, Xianglong, XU, Yitao, ZHANG, Chongzhi, XIE, Xiaofei
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Critical attacking route; Adversarial robustness; Model interpretation; Information Security; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7053; https://ink.library.smu.edu.sg/context/sis_research/article/8056/viewcontent/1_s2.0_S0020025520308124_main.pdf
• Institution: Singapore Management University

Deep neural networks (DNNs) are vulnerable to adversarial examples which are generated by inputs with imperceptible perturbations. Understanding adversarial robustness of DNNs has become an important issue, which would for certain result in better practical deep learning applications. To address thi...