Introducing a Two-step Strategy Based on Deep Learning to Enhance the Accuracy of Intrusion Detection Systems in the Network

Intrusion Detection System is one of the most important security features of modern computer networks that can detect network penetration through a series of functions. This system is independently used (e.g. Snort) or with various security equipment (such as Antivirus, UTM, etc.) on the network and detects an attack based on two techniques of abnormal detection and signature-based detection. Currently, most of the researches in the field of intrusion detection systems have been done based on abnormal behavior using a variety of methods including statistical techniques, Artificial Intelligence (AI), data mining, and machine learning. In this study, we can achieve an effective accuracy using a candidate class of the KDD dataset and deep learning techniques.