Towards characterizing adversarial defects of deep learning software from the lens of uncertainty

• Main Authors: ZHANG, Xiyue, XIE, Xiaofei, MA, Lei, DU, Xiaoning, HU, Qiang, LIU, Yang, ZHAO, Jianjun, SUN, Meng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Deep learning; uncertainty; adversarial attack; software testing; OS and Networks; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7084; https://ink.library.smu.edu.sg/context/sis_research/article/8087/viewcontent/3377811.3380368.pdf
• Institution: Singapore Management University

Over the past decade, deep learning (DL) has been successfully applied to many industrial domain-specific tasks. However, the current state-of-the-art DL software still suffers from quality issues, which raises great concern especially in the context of safety- and security-critical scenarios. Adver...