A Method for Detecting LDoS Attacks in SDWSN Based on Compressed Hilbert-Huang Transform and Convolutional Neural...

Area of Science:

• Computer Science
• Network Security
• Signal Processing

Background:

• Low-Rate Denial of Service (LDoS) attacks pose a significant threat to Software-Defined Wireless Sensor Networks (SDWSNs).
• These attacks are challenging to detect due to their low signal intensity and resource-intensive nature.
• Existing detection methods struggle with the subtle characteristics of LDoS attack signals.

Purpose of the Study:

• To propose an efficient and accurate detection method for LDoS attacks in SDWSNs.
• To address the challenges of detecting small, non-smooth signals characteristic of LDoS attacks.
• To improve the computational efficiency and reduce modal mixing in signal analysis.

Main Methods:

• Utilizing Hilbert-Huang Transform (HHT) for time-frequency analysis of network traffic signals.
• Implementing a compressed HHT to remove redundant Intrinsic Mode Functions (IMFs), enhancing efficiency and eliminating modal mixing.
• Transforming one-dimensional data into two-dimensional temporal-spectral features.
• Employing a Convolutional Neural Network (CNN) for the classification and detection of LDoS attacks.
• Simulating LDoS attacks within the Network Simulator-3 (NS-3) environment for performance evaluation.

Main Results:

• The proposed method successfully transforms one-dimensional data into two-dimensional temporal-spectral features.
• Compressed HHT effectively reduces computational load and mitigates modal mixing.
• Simulations demonstrated the method's capability in detecting various LDoS attack scenarios.
• The detection accuracy for complex and diverse LDoS attacks reached an impressive 99.8%.

Conclusions:

• The developed method offers a highly accurate and efficient solution for detecting LDoS attacks in SDWSNs.
• The integration of compressed HHT and CNN provides a robust framework for analyzing subtle network attack signals.
• This approach significantly enhances the security posture of SDWSNs against sophisticated denial-of-service threats.