L1-TSFW: attention based-CNN AND BI-LSTM model for network intrusion detection

Duohan Xu

doi:10.1117/12.3033053

5 July 2024 L1-TSFW: attention based-CNN AND BI-LSTM model for network intrusion detection

Duohan Xu

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 1318463 (2024) https://doi.org/10.1117/12.3033053
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

With the widespread application of the internet across various societal domains, although it has facilitated information exchange, it has also posed significant threats to individual, societal, and even national security. Consequently, detecting and identifying potential intrusion behaviors in networks has become a crucial means to mitigate network threats. Addressing issues such as high feature dimensionality and weak model adaptability leading to high rates of false positives and false negatives in current network intrusion detection research, this paper utilizes deep learning techniques to construct the intrusion detection model L1-TSFW. Based on the improved density peak clustering algorithm, a feature extraction method leveraging the L1 norm of multiple density peak clusters is proposed for extracting features from raw traffic data, which are then fed into the constructed TSFW module. The TSFW module integrates convolutional neural networks and bidirectional long short-term memory networks to thoroughly learn and explore the spatial and temporal characteristics of the raw data. To address information loss during network learning, an attention mechanism is introduced. Experimental results demonstrate that the proposed model achieves a significant improvement in training time and shows notable enhancements in both increasing model accuracy and accelerating model convergence.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Duohan Xu "L1-TSFW: attention based-CNN AND BI-LSTM model for network intrusion detection", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 1318463 (5 July 2024); https://doi.org/10.1117/12.3033053

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Feature extraction

Computer intrusion detection

Performance modeling

Education and training

Deep learning

Machine learning

Show All Keywords

Keywords/Phrases

Search In:

Publication Years