Malicious sequential pattern mining for automatic malware detection

作者：

Highlights：

• An effective framework using sequence mining technique is proposed for automatic malware detection.

• An efficient sequential pattern mining algorithm for discovering discriminative patterns between malware and benign samples.

• A new nearest neighbor classifier as the detection module to identify unknown malware.

• The strong results of the proposed framework compared with the existing malware detection methods in detecting new malicious samples.

摘要

•An effective framework using sequence mining technique is proposed for automatic malware detection.•An efficient sequential pattern mining algorithm for discovering discriminative patterns between malware and benign samples.•A new nearest neighbor classifier as the detection module to identify unknown malware.•The strong results of the proposed framework compared with the existing malware detection methods in detecting new malicious samples.

论文关键词：Malware detection,Instruction sequence,Sequential pattern mining,Classification

论文评审过程：Received 25 January 2015, Revised 3 January 2016, Accepted 4 January 2016, Available online 11 January 2016, Version of Record 27 January 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.01.002