Hyperparameter Optimization Techniques for CNN-Based Cyber Security Attack Classification

Abstract

Abstract The proliferation of cyber security attacks necessitates advanced and efficient detection methods. This study explores the application of Convolutional Neural Networks (CNNs) for classifying cyber security attacks using a comprehensive dataset containing various attack types and network traffic features. Emphasizing the role of hyperparameter optimization (HPO) techniques, this research aims to enhance the CNN model's performance in accurately detecting and classifying cyber attacks. Traditional machine learning approaches often need to catch up in capturing the complex patterns in such data, whereas CNNs excel in automatically extracting hierarchical features. Using the provided dataset, which includes attributes such as packet length, source and destination ports, protocol, and traffic type, we implemented various (HPO) techniques, including Grid Search, Random Search, and Bayesian Optimization, to identify the optimal CNN configurations. Our optimized CNN model significantly improved classification result. to baseline models without hyperparameter tuning. The results underline the importance of HPO in developing robust CNN models for cybersecurity applications. This study provides a practical framework for leveraging deep learning and optimization techniques to enhance cyber defense mechanisms, paving the way for future advancements in the field.