ROULETTE: A neural attention multi-output model for explainable Network Intrusion Detection

作者：

Highlights：

• Deep Learning systems are increasingly used for Network Intrusion Detection.

• A method for multiclass explainable classification of traffic data is proposed.

• It integrates a learnable attention mechanism with multi-output learning.

• The method provides accurate and explainable decisions.

• Experiments on benchmark datasets showed the effectiveness of the proposed method.

摘要

•Deep Learning systems are increasingly used for Network Intrusion Detection.•A method for multiclass explainable classification of traffic data is proposed.•It integrates a learnable attention mechanism with multi-output learning.•The method provides accurate and explainable decisions.•Experiments on benchmark datasets showed the effectiveness of the proposed method.

论文关键词：Network intrusion detection,Multi-class classification,Deep learning,Attention,Explainable artificial intelligence,Multi-output learning

论文评审过程：Received 27 December 2021, Revised 15 February 2022, Accepted 29 March 2022, Available online 6 April 2022, Version of Record 19 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117144