Design of Intrusion Detection System Based on Improved ABC elite and BP Neural Networks

Letian Duan1, Dezhi Han1 and Qiuting Tian1

  1. College of Information Engineering, Shanghai Maritime University
    Shanghai 201306, China
    1812796760@qq.com, dzhan@shmtu.edu.cn, tqt2018@163.com

Abstract

Intrusion detection is a hot topic in network security. This paper proposes an intrusion detection method based on improved artificial bee colony algorithm with elite-guided search equations (IABC elite) and Backprogation (BP) neural networks. The IABC elite algorithm is based on the depth first search framework and the elite-guided search equations, which enhance the exploitation ability of artificial bee colony algorithm and accelerate the convergence. The IABC elite algorithm is used to optimize the initial weight and threshold value of the BP neural networks, avoiding the BP neural networks falling into a local optimum during the training process and improving the training speed. In this paper, the BP neural networks optimized by IABC elite algorithm is applied to intrusion detection. The simulation on the NSL-KDD dataset shows that the intrusion detection system based on the IABC elite algorithm and the BP neural networks has good classification and high intrusion detection ability.

Key words

Intrusion Detection, Machine Learning, BP Neural Networks, Improved ABC elite

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS181001026D

Publication information

Volume 16, Issue 3 (October 2019)
Recent Advances in Information Processing and Security
Year of Publication: 2019
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Duan, L., Han, D., Tian, Q.: Design of Intrusion Detection System Based on Improved ABC elite and BP Neural Networks. Computer Science and Information Systems, Vol. 16, No. 3, 773–795. (2019), https://doi.org/10.2298/CSIS181001026D