Build intrusion detection model based on CNN and ensemble learning

Chen Chen; Guanghua Wang; Bo Yang; Lintao Yang; Xiaoyan Ye

doi:10.1117/12.2655173

2 November 2022 Build intrusion detection model based on CNN and ensemble learning

Chen Chen, Guanghua Wang, Bo Yang, Lintao Yang, Xiaoyan Ye

Proceedings Volume 12455, International Conference on Signal Processing and Communication Security (ICSPCS 2022); 124550O (2022) https://doi.org/10.1117/12.2655173
Event: International Conference on Signal Processing and Communication Security (ICSPCS 2022), 2022, Dalian, China

Abstract

In order to effectively detect network attacks, machine learning is widely used to classify different types of intrusion detection. Traditional detection usually used a single model to train data, which was prone to the problems of large generalization error and over fitting. In order to solve this problem, the idea of ensemble learning is introduced, and an intrusion detection model based on CNN and ensemble learning is proposed. Firstly, CNN is used to mine the deep information in the original data, and then the mined information is taken as the input and detected by using the ensemble learning model. According to the stacking strategy, a variety of heterogeneous models are used as the base-learner, and support vector machine is selected as the meta-learner. The NSL-KDD dataset is used to train and test the intrusion detection model. The experimental results show that the model can obtain higher accuracy and has very good intrusion detection classification effect.

Citation Download Citation

Chen Chen, Guanghua Wang, Bo Yang, Lintao Yang, and Xiaoyan Ye "Build intrusion detection model based on CNN and ensemble learning", Proc. SPIE 12455, International Conference on Signal Processing and Communication Security (ICSPCS 2022), 124550O (2 November 2022); https://doi.org/10.1117/12.2655173

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available