Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection

作者：

Highlights：

• An ensemble framework of multichannel network anomaly detection model that combines deep autoencoders and the GMM.

• A robust optimization version of EM3 for multiple domains, which transforms the optimization problem of the objective function into a Lagrangian dual.

• We deduce the formula and analyze the convergence of the full text, and prove that our model has stability and robustness.

• To the best of our knowledge is the first work that performs algorithms on both differentiated data domains and data distributions.

摘要

•An ensemble framework of multichannel network anomaly detection model that combines deep autoencoders and the GMM.•A robust optimization version of EM3 for multiple domains, which transforms the optimization problem of the objective function into a Lagrangian dual.•We deduce the formula and analyze the convergence of the full text, and prove that our model has stability and robustness.•To the best of our knowledge is the first work that performs algorithms on both differentiated data domains and data distributions.

论文关键词：Multidomain data,Cyberattacks,Deep autoencoder,GMM

论文评审过程：Received 14 September 2021, Revised 29 November 2021, Accepted 10 December 2021, Available online 10 January 2022, Version of Record 10 January 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102844