G3MD: Mining frequent opcode sub-graphs for metamorphic malware detection of existing families

作者：

Highlights：

• We hypothesize that metamorphic malwares of a certain family share some sub-structures.

• We propose an approach based on mining frequent sub-graphs.

• We achieved dramatically high precision (over 99% in most cases).

摘要

•We hypothesize that metamorphic malwares of a certain family share some sub-structures.•We propose an approach based on mining frequent sub-graphs.•We achieved dramatically high precision (over 99% in most cases).

论文关键词：Metamorphic malware,Graph mining,Opcode graph,Malware classification and detection,Obfuscation

论文评审过程：Received 27 September 2017, Revised 25 May 2018, Accepted 6 June 2018, Available online 19 June 2018, Version of Record 19 June 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.06.012