Prof. Maode Ma (IET Fellow)

Qatar University, Katar

Prof. Maode Ma, a Fellow of IET, received his Ph.D. from the Department of Computer Science at the Hong Kong University of Science and Technology in 1999. Prof. Ma is a Full Professor in the Faculty of Computer Science and Artificial Intelligence at Shenzhen University of Advanced Technology. Before joining SUAT, he had been a faculty member at Nanyang Technological University and Qatar University for over 25 years. He has extensive research interests in network security, AI security, and wireless networking. He has about 550 international academic publications, which include more than 280 journal papers. His publication has received close to 13,000 citations in Google Scholar. Prof. Ma currently serves as the Editor-in-Chief of the Journal of Communication and Network Security, the International Journal of Computer and Communication Engineering, and the Journal of Communications. He also serves as a Senior Editor for IEEE Communications Surveys and Tutorials, and an Associate Editor for the International Journal of Communication Systems. Prof. Ma is a senior member of the IEEE Communication Society. Prof. Ma has been a Distinguished Lecturer for the IEEE Communication Society from 2013 to 2016 and from 2023 to 2024.

Title: Design of An Automatic Incremental Lifetime Learning IDS 

Abstract: Traditional Intrusion Detection Systems(IDSs) provide limited defense against emerging threats, as they rely on static rules or machine learning (ML) models that lack the capacity for real-time updates. The Incremental Lifetime Learning IDS (ILL-IDS) is a new type of IDS to address this limitation by enabling adaptive learning of new attack types. However, ILL-IDS depends heavily on large volumes of high-quality labeled data, making the model update process costly and labor-intensive. In this talk, the Automatic Incremental Lifetime Learning IDS (AILL-IDS) is intraduced, which is a novel IDS framework that can significantly reduce the need for labelling data by incremental semi-supervised learning. This approach not only enables AILL-IDS to detect unknown types of attacks and adapt its model dynamically with minimal labeled data but also ensures continuous detection during the model update process, enhancing both speed and accuracy in threat detectioninvehicularnetworks or Internet of Thing (IoT) systems. Experimental results demonstrate that AILL-IDS can achieve a high detection rate of 0.97 and an average F1 score of 0.90, labelling only 5.5% of the total traning data, thereby offering an efficient and scalable solution for securing IoT against emerging cyber threats.