|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Cyber threats are increasing and to mitigate cyber attacks and threats, intrusion detection system is introduced. Intrusion detection systems are widely used to capture the deviating patterns in the network traffic. Due to dynamic nature of changing patterns of threats and attacks, an efficient model is required to update the attacks and patterns present in the network traffic data. Many machine learning models are deployed to learn the traffic patterns but traditional models largely suffer from high traffic volume and high dimensional features. This paper proposes a deep learning model which is resilient to capture network intrusions with better learning ability. The effectiveness of the proposed deep learning model is demonstrated using CICIDS2017 dataset and the performance of the proposed model achieved accuracy of 99.7% over other machine learning models.
Keyword
#
PDF Download (click here)
|
|
|
|
|