An empirical study on correlation between coverage and robustness for deep neural networks

• Main Authors: DONG, Yizhen, ZHANG, Peixin, WANG, Jingyi, LIU, Shuang, SUN, Jun, HAO, Jianye, WANG, Xinyu, WANG, Li, DONG, Jinsong, DAI, Ting
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Complex networks; Deep neural networks; Face recognition; Malware; Safety engineering; Statistical tests; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/5942; https://ink.library.smu.edu.sg/context/sis_research/article/6945/viewcontent/Emp_coverage_robustness_DNN_2020_av.pdf
• Institution: Singapore Management University

Deep neural networks (DNN) are increasingly applied in safety-critical systems, e.g., for face recognition, autonomous car control and malware detection. It is also shown that DNNs are subject to attacks such as adversarial perturbation and thus must be properly tested. Many coverage criteria for DN...