Summary

International Symposium on Nonlinear Theory and its Applications

2017

Session Number:A2L-C

Session:

Number:A2L-C-2

Fast Construction of an Updating System for Intrusion Detection Using a Multi-Layer Extreme Learning Machine

Daichi Noguchi,  Masaharu Adachi,  

pp.144-147

Publication Date:2017/12/4

Online ISSN:2188-5079

DOI:10.34385/proc.29.A2L-C-2

PDF download (579.8KB)

Summary:
Fast construction for an intrusion detection system (IDS) enables rapid detection of, and response to, intrusions into a network. Using deep neural networks is expected to give a high detection rate for an IDS (S.Poluluri, et al., EFTA2016, pp.1-8). However, this requires time-consuming iterative computation. To address this, we propose a method for fast construction of an IDS using a multi-layer Extreme Learning Machine based on Auto Encoder.