MARK-ELM: Application of a novel Multiple Kernel Learning framework for improving the robustness of Network Intrusion Detection

作者：

Highlights：

• Apply Multiple Kernel Boosting and Multiclass KELM to Network Intrusion Detection.

• Tested approach on several machine learning datasets and the KDD Cup 99 dataset.

• Utilized Fractional Polynomial Kernels for the Network ID problem for the first time.

• Requires no feature selection, minimal pre-processing and works on imbalanced data.

• Achieves superior detection rates and lower false alarm rates than other approaches.

摘要

•Apply Multiple Kernel Boosting and Multiclass KELM to Network Intrusion Detection.•Tested approach on several machine learning datasets and the KDD Cup 99 dataset.•Utilized Fractional Polynomial Kernels for the Network ID problem for the first time.•Requires no feature selection, minimal pre-processing and works on imbalanced data.•Achieves superior detection rates and lower false alarm rates than other approaches.

论文关键词：Network Intrusion Detection,KDD Cup 1999,Multiple Kernel Learning,Machine Learning,Extreme Learning Machine,Ensemble Learning,Adaptive Boosting,Cyber security,Multiclass Classification,Kernel Selection,Fractional Polynomial Kernels

论文评审过程：Available online 31 December 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.12.040