Web traffic anomaly detection using C-LSTM neural networks

作者：

Highlights：

• We propose a C-LSTM neural network for effectively detecting anomalies in web traffic data.

• CNN extracts spatial features and LSTM models temporal characteristics.

• It outperforms the machine learning methods for Yahoo's Webscope S5 dataset.

• We reveal the internal operation of anomaly detection process by t-SNE algorithm.

摘要

•We propose a C-LSTM neural network for effectively detecting anomalies in web traffic data.•CNN extracts spatial features and LSTM models temporal characteristics.•It outperforms the machine learning methods for Yahoo's Webscope S5 dataset.•We reveal the internal operation of anomaly detection process by t-SNE algorithm.

论文关键词：Web traffic,Anomaly detection,Deep learning,C-LSTM

论文评审过程：Received 16 January 2018, Revised 3 April 2018, Accepted 4 April 2018, Available online 5 April 2018, Version of Record 13 April 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.04.004