URL filtering using big data analytics in 5G networks

Author links open overlay panelNasir AliKhanaAbidKhanbMansoorAhmadacMunam AliShahaGwanggilJeond

Show moreAdd to Mendeley

Share

Cite

https://doi.org/10.1016/j.compeleceng.2021.107379Get rights and content

ABSTRACT

The future generations networking technologies such as 5G and 6G will provide tremendous performance, network capacity, quality of service and connectivity. Therefore, the convergence of these with technologies with big data analytics in today's smart ecosystem will provide tremendous opportunities. The existing URL filtering techniques do not do real-time filtering, and lack fault-tolerance and scalability. We have addressed these issues and have developed a real-time, fault-tolerant and scalable machine learning based binary classification model, which handles streams of URL traffic and classifies it into obscene or clean material, in real-time. We have only used the URL based features for classification, and have still achieved a good accuracy of 93% on logistic regression classifier and 88%. Our model can filter 2 million URLs in 55 seconds. The proposed model achieved precision, recall and f1-score values of 0.92, 0.95 and 0.93 respectively.

Graphical abstract

1. Download : Download high-res image (73KB)
2. Download : Download full-size image

• Previous article in issue
• Next article in issue

Keywords

Big data analytics

URL filtering

Machine learning

Logistic regression

Nasir Ali Khan did his MS in computer science from COMSATS University Islamabad (CUI), Islamabad Pakistan. His research interests include big data analytics, security & privacy in distributed systems including cloud computing, machine learning and AI.

Abid Khan is with the department of computer science, Aberystwyth University, Aberystwyth, Wales, UK. His research interests include applied cryptography, security & privacy in distributed systems. He was a PostDoc fellow at e-security laboratory of Politecnico De Torino, Italy 2009-2011. He was awarded the prestigious fellowship for young researcher by Politecnico De Torino for his postdoctoral research.

Mansoor Ahmed is a research fellow at Innovative Value Institute, Maynooth University Ireland under a Marie Sklodowska-Curie Actions (MSCA) /EU research funded project. He did his PhD from Vienna University of technology and postdoc fellow from Indiana University, USA and UCD, Ireland in 2011 and 2017. His research interest includes Semantic Web technologies, Information Security and Privacy.

Munam Ali Shah received the B.Sc. and M.Sc. degrees in computer science from the University of Peshawar, Pakistan, in 2001 and 2003, respectively, the M.S. degree in security technologies and applications from the University of Surrey, U.K., in 2010, and the Ph.D. degree from the University of Bedfordshire, U.K., in 2013. His research interests include computer networks and security.

Gwanggil Jeon received the B.S., M.S., and Ph.D. degrees from the Department of Electronics and Computer Engineering, Hanyang University, Seoul, Korea, in 2003, 2005, and 2008, respectively. Currently, he is Professor at Xidian University, Xian, China and Incheon National University, Incheon, Korea.