A Comparative study of intrusion detection systems applied to NSL-KDD Dataset

Eshak Magdy, Mina; M. MATTER, AHMED; HUSSIN, SALEH; HASSAN, DOAA; Elsaid, Shima

doi:10.21608/eijest.2022.137441.1156

A Comparative study of intrusion detection systems applied to NSL-KDD Dataset

Document Type : Original Article

Authors

¹ Electronics and Communications Dep., Faculty of Engineering, Zagazig University, Zagazig, Egypt

² Department of computer engineering and artificial intelligence, military technical college

³ Computers and Systems Department, National Telecommunication Institute, Cairo, Egypt. research scholar Indiana University - Purdue University Indianapolis (IUPUI).

⁴ Electronics and Communications Dep., Faculty of Engineering, Zagazig University, Zagazig, Egypt.

10.21608/eijest.2022.137441.1156

Abstract

Almost every day a new cyber-attack is born; these attacks are more sophisticated than anterior times. However, there is a hope that researchers can develop new techniques to afford discoverability and prevention capabilities against cyber-attacks as soon as possible. For this sake, many papers were providing machine learning and Deep learning techniques that applied to cyber security and intrusion datasets, in order to enhance the detection and prevention of the aforementioned attacks. In this paper we will provide a comparative study of intrusion detection system papers that applied machine learning and Deep learning techniques to the NSL-KDD dataset. Cyber security is a mandatory technology in a world where cyber-attacks are increased exponentially; to ensure that assets are protected from cyber-attacks many security measures must be applied. Cybercrimes cost our world too much loss as it's expected to reach up to six trillion Dollars by the end of year 2021, and these losses are horrible for both technology and economy.

Keywords