Xavier Bellekens

University of Strathclyde, Glasgow, Electronic and Electrical Engineering, Faculty Member

Followers

256

Following

Co-authors

Public Views

Xavier Bellekens is a Lecturer (Assistant Professor) Chancellor’s Fellow in the Institute for Signals, Sensors and Communications with the Department of Electronic and Electrical Engineering at the University of Strathclyde. Prior to this position, Xavier was a Lecturer (Assistant Professor) in Security and Privacy in the Division of Cyber-Security at the University of Abertay in Dundee, and the the head of the Machine Learning for Cyber Security Research Group. Prior to joining the University of Abertay, Xavier was a Research Assistant and Associate in the Centre for Intelligent Dynamic Communications at the University of Strathclyde, Glasgow, working on cyber-physical security for critical infrastructures. Xavier is the Chair of the IEEE Cyber Science collocated conferences, a reviewer for world leading academic conferences and journals and is the Education Cyber-Security Thematic Leader and Scottish Blockchain Outreach leader for IEEE UK and Ireland . He is also a regular contributor to Belgian and UK Radio and Newspaper on Cyber-Security and Hacking related topics.

Research Interests
My research explores the field cyber-security from situational awareness and training, to the use of blockchain for privacy and vehicular technologies. I enjoy exploring and combining different fields of computer science to improve system security. Most recently, I have been exploring the intersection between machine learning and cyber-security and applying my research to protect critical infrastructures including (Power Plants, Vehicular, Avionics and Naval architectures).

I work towards providing usable solutions to challenging technical problems. This has led me to work with academic and industrial partners from around the world (Europe, America and Asia)
Address: United Kingdom

less

InterestsView All (49)

Uploads

Papers by Xavier Bellekens

Utilising Deep Learning Techniques for Effective Zero-Day Attack Detection

by Xavier Bellekens and Hanan Hindy

Machine Learning (ML) and Deep Learning (DL) have been used for building Intrusion Detection Syst... more Machine Learning (ML) and Deep Learning (DL) have been used for building Intrusion Detection Systems (IDS). The increase in both the number and sheer variety of new cyber-attacks poses a tremendous challenge for IDS solutions that rely on a database of historical attack signatures. Therefore, the industrial pull for robust IDSs that are capable of flagging zero-day attacks is growing. Current outlier-based zero-day detection research suffers from high false-negative rates, thus limiting their practical use and performance. This paper proposes an autoencoder implementation for detecting zero-day attacks. The aim is to build an IDS model with high recall while keeping the miss rate (false-negatives) to an acceptable minimum. Two well-known IDS datasets are used for evaluation-CICIDS2017 and NSL-KDD. In order to demonstrate the efficacy of our model, we compare its results against a One-Class Support Vector Machine (SVM). The manuscript highlights the performance of a One-Class SVM when zero-day attacks are distinctive from normal behaviour. The proposed model benefits greatly from autoencoders encoding-decoding capabilities. The results show that autoencoders are well-suited at detecting complex zero-day attacks. The results demonstrate a zero-day detection accuracy of 89-99% for the NSL-KDD dataset and 75-98% for the CICIDS2017 dataset. Finally, the paper outlines the observed trade-off between recall and fallout.

Xavier Bellekens

Uploads

Papers by Xavier Bellekens

Log In