Detection of distributed denial-of-service (DDoS) attacks with crow search optimization algorithm and artificial neural network

This study proposes a novel approach to detect Distributed Denial of Service (DDoS) attacks using the Crow Search Optimization Algorithm (CSOA) for feature dimensionality reduction combined with Artificial Neural Network (ANN) classification. CSOA effectively reduces feature redundancy, optimizing relevant features for improved accuracy. After feature reduction, ANN is trained on the optimized set to classify normal and attack traffic. Various optimization algorithms, including Genetic Algorithm (GA), Ant Colony Optimization (ACO), and Particle Swarm Optimization (PSO), were evaluated for comparison. GA achieved an accuracy of 96.10%, while ACO and PSO performed slightly better, reaching 97.08% and 97.01% respectively. The proposed CSOA-ANN method outperformed all other algorithms with an accuracy of 98.50%, precision of 98.94%, recall of 98.04%, and F1 score of 98.49%. This approach not only demonstrates high accuracy but also offers an efficient and energy-saving solution, making it an optimal choice for network security in DDoS detection. The CSOA-ANN model’s effectiveness in enhancing classification accuracy underscores its potential for robust intrusion detection in cybersecurity applications.