Authors: Kexin Pei, Yinzhi Cao, Junfeng Yang, Suman Jana
Published: 2019-10-24
DOI: 10.1145/3361566
Source: Full article
Deep learning (DL) systems are increasingly deployed in safety- and security-critical domains such as self-driving cars and malware detection, where the correctness and predictability of a system's behavior for corner case inputs are of great importance. Existing DL testing depends heavily on manually labeled data and therefore often fails to expose erroneous behaviors for rare inputs.