Android malware concept drift using system calls: Detection, characterization and challenges

作者：

Highlights：

• Demonstrates the existence of concept drift issues in Android malware detection.

• Proposes a novel detection system to address concept drift in Android malware.

• Demonstrates the usefulness of a small set of system calls as detection features.

• Compares the impact and usefulness of different timestamps to handle concept drift.

• Performs the characterization of the observed concept drift.

摘要

•Demonstrates the existence of concept drift issues in Android malware detection.•Proposes a novel detection system to address concept drift in Android malware.•Demonstrates the usefulness of a small set of system calls as detection features.•Compares the impact and usefulness of different timestamps to handle concept drift.•Performs the characterization of the observed concept drift.

论文关键词：Concept drift,Android malware,System calls,Mobile malware,Malware characterization,Malware detection,Malware evolution,Malware behavior

论文评审过程：Received 12 September 2021, Revised 7 April 2022, Accepted 7 April 2022, Available online 21 April 2022, Version of Record 28 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117200