A Behaviour Profiling Based Technique for Network Access Control Systems

• Published in: International journal of cyber-security and digital forensics Vol. 8; no. 1; pp. 23 - 30
• Main Authors: Muhammad, Musa Abubakar, Ayesh, Aladdin
• Format: Journal Article
• Language: English
• Published: The Society of Digital Information and Wireless Communications 01.01.2019
• Subjects: Actuators; Algorithms; Control equipment; Control systems; Criminal investigation; Data security; Internet of things; Job satisfaction; Methods; Novels; Retirement benefits; Smart phones; Technology; Technology application; Telecommunications equipment industry; Third generation wireless technology; Finland
• ISSN: 2305-0012; 2305-0012
• DOI: 10.17781/P002537

The emergence of the Internet of Things (IoT) has lead to a technological transformation that integrates several technologies to represent the future of computing and communications. IoT is the interconnection of internet of computing devices embedded in objects such as sensors, actuators and networks enabling them to send and receive data. Bring Your Own Device (BYOD) is an integral part of IoT, which is the practice of allowing employees to use their own smartphones, tablets and laptops in the workplace to access enterprise resources and applications. It offers several benefits like employee job satisfaction, productivity, increased job efficiency and flexibility. With all the advantages offered, BYOD environments are still less safe because of persistent security threats, attacks caused by loss, theft of personal devices and corporate data leakage. BYOD enterprise network is accessed through enterprise mobility management solutions which monitor, controls and enforce access control policies to devices accessing the network. This paper aims to close the gap of the existing Network Access Control (NAC) systems focusing on 802.1x protocols with a Novel Device type Behaviour Profiling Technique. The Behaviour Profiling Technique used a dataset proposed in [29] to develop a device type behaviour profiles of five dell netbooks, three iPads, two iPhones 3G, two iPhones 4G and two Nokia Phones using K-Means Clustering Algorithm. Index Terms--BYOD security, Behaviour profiling, device fingerprinting, k-means clustering, anomaly detection.