Title: Machine learning techniques for automated policy violation reporting

Authors: Albara Awajan; Moutaz Alazab; Salah Alhyari; Issa Qiqieh; Mohammad Wedyan

Addresses: Faculty of Artificial Intelligence, Al-Balqa Applied University, Al-Salt, Jordan ' Faculty of Artificial Intelligence, Al-Balqa Applied University, Al-Salt, Jordan ' Computer Operation Department, JEPCO, Amman, Jordan ' Faculty of Engineering, Al-Balqa Applied University, Al-Salt, Jordan ' Faculty of Artificial Intelligence, Al-Balqa Applied University, Al-Salt, Jordan

Abstract: Citizens regularly face incidents or violations and even digital security incidents such as e-mail intrusion, system infiltration or damage caused by malicious software. These violations are usually left unreported because of the difficulties that the citizens face to get the incident reported. Another issue is that many complaints should be handled by different departments in different sectors, but due to a lack of cooperation between departments in different sectors, complaints are frequently misplaced. To solve this problem, we propose an automated client-server citizen reporting system framework based on machine learning techniques. The paper focuses on the design and implementation of an automated image feature-based classification framework that jointly uses feature extraction and deep learning to classify the images and forward them to the relevant department. In addition, the framework permits users to report about any cyber-crime incidents such as bank account intrusion (Alazab et al., 2011a, 2020b; Alazab, 2020), credit card fraud (Alazab et al., 2011b, 2012a, 2012c), phishing and pharming. The results show that complaints handling accuracy is up to 95.4%.

Keywords: cyber security; crime violation; mobile security; reporting system; digital forensics; deep learning.

DOI: 10.1504/IJITST.2022.10048153

International Journal of Internet Technology and Secured Transactions, 2022 Vol.12 No.5, pp.387 - 405

Accepted: 15 Aug 2021
Published online: 28 Sep 2022 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article