Integrating hybrid bald eagle crow search algorithm and deep learning for enhanced malicious node detection in secure...

Area of Science:

• Computer Science
• Cybersecurity
• Artificial Intelligence

Background:

• Distributed systems face security challenges due to independent units and potential single points of failure.
• Malicious node detection is critical for ensuring the safety and reliability of distributed methods.
• Existing methods often combine anomaly detection, machine learning, cryptography, and intrusion detection systems.

Purpose of the Study:

• To design and evaluate a novel technique for enhanced malicious node detection in secure distributed systems.
• To improve the robustness and accuracy of identifying malicious nodes within distributed environments.
• To introduce a hybrid approach integrating metaheuristic optimization with deep learning for superior detection capabilities.

Main Methods:

• The Hybrid Bald Eagle-Crow Search Algorithm and Deep Learning for Enhanced Malicious Node Detection (HBECSA-DLMND) technique was developed.
• Data normalization (Linear Scaling Normalization - LSN) and class imbalance handling (ADASYN) were performed.
• Metaheuristic feature selection using Hybrid Bald Eagle-Crow Search Algorithm (HBECSA) and Convolutional Sparse Autoencoder (CSAE) for detection, with Dung Beetle Optimization (DBO) for parameter tuning.

Main Results:

• The HBECSA-DLMND technique demonstrated a high detection accuracy of 98.99% on the WSN-DS benchmark dataset.
• The hybrid approach effectively selected optimal features and accurately identified malicious nodes.
• Performance validation showed superior results compared to existing malicious node detection methods.

Conclusions:

• The HBECSA-DLMND technique offers a significant advancement in securing distributed systems against malicious nodes.
• The integration of metaheuristic algorithms and deep learning provides a powerful framework for robust intrusion detection.
• The study highlights the effectiveness of the proposed method in enhancing the overall security and reliability of distributed environments.