Novel set of general descriptive features for enhanced detection of malicious emails using machine learning methods
作者：
Highlights：
• We propose a novel set of general descriptive features for malicious email detection.
• We leverage our features with ML for the detection of malicious email.
• Our novel set of features enhances the detection of malicious email using ML.
• The classifier which provided the best detection capabilities was Random Forest.
• The best detection results were AUC = 0.929, TPR = 0.947, and FPR = 0.03.
摘要
•We propose a novel set of general descriptive features for malicious email detection.•We leverage our features with ML for the detection of malicious email.•Our novel set of features enhances the detection of malicious email using ML.•The classifier which provided the best detection capabilities was Random Forest.•The best detection results were AUC = 0.929, TPR = 0.947, and FPR = 0.03.
论文关键词：Email,Detection,Machine learning,Analysis,Malware,Features
论文评审过程：Received 1 October 2017, Revised 12 February 2018, Accepted 29 May 2018, Available online 31 May 2018, Version of Record 18 June 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.05.031
