Adaptive intrusion detection via GA-GOGMM-based pattern learning with fuzzy rough set-based attribute selection

作者：

Highlights：

• Pattern learning-based network intrusion detection (NID) method is proposed.

• Intrinsic attribute subset is achieved based on fuzzy rough set theory.

• Greedy algorithm-based global optimal GMM is introduced for pattern representation.

• Online NID model updating strategy is introduced based on frequency pattern mining.

摘要

•Pattern learning-based network intrusion detection (NID) method is proposed.•Intrinsic attribute subset is achieved based on fuzzy rough set theory.•Greedy algorithm-based global optimal GMM is introduced for pattern representation.•Online NID model updating strategy is introduced based on frequency pattern mining.

论文关键词：Intrusion detection system,Gaussian mixture model,Greedy algorithm,Fuzzy rough set,Information gain ratio,Pattern learning

论文评审过程：Received 3 May 2019, Revised 9 July 2019, Accepted 25 July 2019, Available online 26 July 2019, Version of Record 1 August 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112845