A comparative evaluation of unsupervised deep architectures for intrusion detection in sequential data streams

作者：

Highlights：

• Thorough comparison of recurrent neural networks for anomaly detection.

• Introduction of attentional component enabling explanations for end-users.

• Evaluation focusing on ranking metrics with end-users in mind.

摘要

•Thorough comparison of recurrent neural networks for anomaly detection.•Introduction of attentional component enabling explanations for end-users.•Evaluation focusing on ranking metrics with end-users in mind.

论文关键词：Deep learning,Intrusion detection,Anomaly detection,Real-world data

论文评审过程：Received 15 April 2019, Revised 6 March 2020, Accepted 15 May 2020, Available online 27 May 2020, Version of Record 11 June 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113577