Reducing false positives of network anomaly detection by local adaptive multivariate smoothing

作者：

Highlights：

• Using LAMS to improve the output of network anomaly detection systems.

• LAMS reduces the amount of structured and unstructured false positives.

• Improvement in AUC shown on various malicious activities and two different anomaly detection systems.

摘要

•Using LAMS to improve the output of network anomaly detection systems.•LAMS reduces the amount of structured and unstructured false positives.•Improvement in AUC shown on various malicious activities and two different anomaly detection systems.

论文关键词：Network anomaly detection,Regression smoothing,False positive rate reduction

论文评审过程：Received 31 August 2015, Revised 6 March 2016, Accepted 17 March 2016, Available online 4 April 2016, Version of Record 15 September 2016.

论文官网地址：https://doi.org/10.1016/j.jcss.2016.03.007