Can we trust your explanations? Sanity checks for interpreters in android malware analysis

• Main Authors: FAN, Min, WEI, Wenying, XIE, Xiaofei, LIU, Yang, GUAN, Xiaohong, LIU, Ting
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Android malware; Explanation approaches; Stability; Robustness; Effectiveness; Information Security; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7101; https://ink.library.smu.edu.sg/context/sis_research/article/8104/viewcontent/2008.05895.pdf
• Institution: Singapore Management University

With the rapid growth of Android malware, many machine learning-based malware analysis approaches are proposed to mitigate the severe phenomenon. However, such classifiers are opaque, non-intuitive, and difficult for analysts to understand the inner decision reason. For this reason, a variety of exp...