NETWORK CYBERSECURITY INCIDENTS MULTICLASSIFICATION BASED ON DEEP LEARNING
Rasim Mahammad Alguliyev, Ramiz Shikhaliyev · Problems of Information Technology · 2024
The rapid increase in network traffic and the growing complexity of cyberattacks have rendered traditional cybersecurity monitoring methods insufficient for effectively detecting and classifying network incidents. To overcome these limitations, we present a deep learning-based approach that utilizes a hybrid architecture, combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) models, for the multi-classification of cybersecurity incidents. Our model is trained on the CICIDS2017 dataset, which encompasses a wide range of attack types. The hybrid CNN-LSTM model achieved a classification accuracy of 96.76% and an error rate of 9.34%, showcasing its ability to accurately detect and classify various cybersecurity threats. This approach offers a robust solution for enhancing the detection and classification of network cybersecurity incidents.