Can I read A Hybrid Autoencoder and Density Estimation Model for Anomaly Detection on EtoBox?

A Hybrid Autoencoder and Density Estimation Model for Anomaly Detection by Van Loi Cao; Miguel Nicolau; James McDermott is a book available to read on EtoBox.

What is A Hybrid Autoencoder and Density Estimation Model for Anomaly Detection about?

A novel one-class learning approach is proposed for network anomaly detection based on combining autoencoders and density estimation. An autoencoder attempts to reproduce the input data in the output layer. The smaller hidden layer becomes a bottleneck, forming a compressed representation of the data. It is now proposed to take low density in the hidden layer as indicating an anomaly. We study two possibilities for modelling density: a single Gaussian, and a full kernel density estimation. The methods are tested on the NSL-KDD dataset, and experiments show that the proposed methods out-perform best-known results on three out of four sub-datasets.

Author

Van Loi Cao; Miguel Nicolau; James McDermott

Publisher

Springer International Publishing : Imprint : Springer

Published

2016

Language

EN

ISBN

9783319458229

Subjects

Science, Computer Science, Mathematics