An ecosystem for anomaly detection and mitigation in software-defined networking

作者：

Highlights：

• Ecosystem for anomaly detection and mitigation in Software-defined Networking.

• Traffic profiling and anomaly detection tasks operate autonomously.

• The system employs a multi-feature analysis to profile the normal traffic usage.

• Mitigation policy is chosen according to the recognized anomalies.

• Our system outstanding in terms of accuracy and low false-positive rate.

摘要

•Ecosystem for anomaly detection and mitigation in Software-defined Networking.•Traffic profiling and anomaly detection tasks operate autonomously.•The system employs a multi-feature analysis to profile the normal traffic usage.•Mitigation policy is chosen according to the recognized anomalies.•Our system outstanding in terms of accuracy and low false-positive rate.

论文关键词：Anomaly detection,Software-defined networking (SDN),OpenFlow,Multinomial logistic regression

论文评审过程：Received 24 November 2017, Revised 11 February 2018, Accepted 14 March 2018, Available online 15 March 2018, Version of Record 26 March 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.03.027