An Efficient Recurrent Neural Network based Classification Method for Cyber Threat Detection Analysis

Abstract

Cyber threat detection plays an important role in ensuring information security, and the key technology is to accurately identify various attacks in the network. Security of the computer systems is the most important factor for single users and businesses, because an attack on a system can cause data loss and considerable harm to the business. Due to the increment of the range of the cyber-attacks, antivirus scanners cannot fulfill the need for protection. Hence, the increment of the skill level that required for the development of cyber threats and the availability of the attacking tools on the internet, the need for Artificial Intelligence based systems, is a must to the users. In this study, an intrusion detection system based on deep learning, and proposes a deep learning approach for intrusion detection using Efficient Recurrent Neural Networks (ERNN). Moreover, the performance of the model in binary classification and multiclass classification, and the number of neurons and different learning rate impacts on the performance of the proposed model. We compare it with those of Recurrent Neural Network and Support Vector Machine proposed by previous researchers on the benchmark dataset. The experimental results show that ERNN intrusion detection system is very suitable for modeling a classification method with high accuracy and that its performance is superior to that of traditional machine learning classification methods. The ERNN cyber threat detection method improves the accuracy of the intrusion detection and provides a new research method for cyber threat detection.