Tutorial 1: Cybersecurity Challenges and Opportunities for Artificial Intelligence in B5G and 6G Networks

Dr Glaucio H.S. Carvalho, Brock University, Ontario, Canada

Dr. Glaucio H.S. Carvalho is a cross-appointed Assistant Professor of Computer Science and Engineering at Brock University, ON, Canada. He holds a PhD in Computer Science from Toronto Metropolitan University (formerly, Ryerson University) and a PhD in Electrical Engineering from Federal University of Para, Brazil. His research interests are offensive security and defensive science and their applications on critical infrastructure. Dr. Carvalho is currently addressing the security of B5G and 6G telecommunication systems considering topics such as AI-empowered solutions, zero-trust solutions, security- and dependability-aware resource management, and edge-cloud native solutions.


To properly safeguard beyond fifth generation (B5G) and the six generation (6G) networks against the evolving cyber threat landscape in a sustainable and scalable way, innovative cybersecurity approaches should be conceived. In this arena, Artificial Intelligence (AI) stands out as a promising solution. Undeniably, the AI capability of discovering hidden patterns and signatures in a large set of time-varying multi-dimensional data arises as a compelling feature to be used by Mobile Network Operators (MNOs) to improve the cybersecurity situational awareness and achieve a smart, agile, flexible, timely, and cost-effective self-X (i.e., self-organizing, self-healing, self-optimizing, self-service) security management. However, the benefits of an AI-empowered cybersecurity framework can be undermined by its vulnerabilities. Indeed, by exploiting the AI’s vulnerabilities, a cyber-criminal can compromise the self-X operation of B5G and 6G network and wreak havoc the performance and reliability of the systems. In this presentation, we are going to present the opportunities for AI to fortify the cybersecurity awareness and decision-making process in B5G/6G systems as well as the challenges that it might face to maintain the cyber resilience of the system.

Table of Content:
1. Introduction 2. B5G and 6G Systems 3. AI-Empowered Cybersecurity 4. Opportunities for AI-Empowered Cybersecurity 5. Challenges for AI-Empowered Cybersecurity 6. Conclusion

Tutorial 2: Multi-Radio Access Technologies for Smart Cities

Dr Simon Chege, University of KwaZulu-Natal, South Africa

Simon Chege received the B.Tech. degree in Electrical and Communications Engineering from Moi University, Kenya in 2010, the MTech. degree in Electrical and Electronic Engineering from JNTU- Anantapur, India in 2017 and PhD in Electronic Engineering at University of KwaZulu-Natal, Durban, South Africa in 2022. He is a registered member of IEEE, Institute of Engineers of Kenya (IEK) and Engineers Board of Kenya (EBK). Currently, his research interests include wireless communications and multiple access technologies for 5G networks and beyond. He has authored and reviewed several papers in high reputed conferences and journals.


With the current trends, what would constitute efficient radio access protocols for the networking architectures deployed in smart cities? Modern smart cities are expected to support diverse quality of service (QoS) application requirements of ultra-low latency, ultra-reliability and enhanced data rates for the surging number of massively connected devices. These ubiquitous service requirements necessitate a paradigm infrastructural and architectural shift in the access of the scarce wireless networks radio spectrum, network heterogeneity, traffic intelligence and management, energy and cost efficiency and latency management. Non-orthogonal multiple access (NOMA) technologies enhance the spectral efficiency by allowing multiple access to resources albeit aggregated interference and increased receiver complexity. By designing hybrid NOMA schemes, the associated near-optimal resource allocation algorithms and multi-user detectors, hybrid NOMA promise to support the QoS requirements for the smart, vehicle to everything (V2I) and IoT devices in smart cities.

Table of Content:
1. Introduction
2. Motivation
3. Potential Facilitators
4. Multi-Radio Access Technologies for Smart Cities
5. World Smart Cities
6. Conclusion

Tutorial 3: Machine Learning for Detecting Cyber Attacks on The Internet of Medical Things

Dr Wei Lu, Professor, Keene State College, The University System of New Hampshire, USA

Wei Lu is a full professor of computer science at Keene State College with The University System of New Hampshire. Before moving to the United States, he worked for several years in the software industry, including as a member of research staff with the German Research Center for Artificial Intelligence (DFKI GmbH), a secure software engineer with a start-up company Q1 Labs, acquired later by IBM as its Security Systems Division, and a Junior Member of Technical Staff (MTS-1) with Bell Labs (Asia & Pacific). He received his Ph.D. in the School of Engineering and Computer Science at the University of Victoria (UVic), Canada, and dual degrees in M.I.P and M.B.A from Franklin Pierce School of Law and Peter T. Paul College of Business and Economics both at the University of New Hampshire (UNH), and M.S./B.S. in Electronics and Information Engineering from the Special Class for the Gifted Young, Huazhong University of Science and Technology (HUST). His general research interests include Data Science, Cybersecurity, and Artificial Intelligence, where he has about 50 papers published by peer-reviewed journals, book chapters, and conference proceedings, that have been cited about 6,000 times according to Google scholar. In addition, he is currently a principal investigator of an NIH-sponsored research project "Securing the Internet of Medical Things in Healthcare with Machine Learning", a Senior Member of IEEE, a recipient of the 2021 KSC-USNH Faculty Distinction in Research and Scholarship Award, serves as a Chair of Computer Society at the IEEE New Hampshire Section, and authored two books published by Springer.


The Internet of Medical Things (IoMT) refers to a connected infrastructure of medical devices, software applications, healthcare information systems, and digital health services, where the connected medical devices create, collect, analyze and transport health data information or medical images to either a cloud computing facility or internal servers via the healthcare provider networks. The recent rise of IoMT has rapidly changed the current healthcare industry, its widespread use in hospitals, however, has also paved a way for a large number of cybercriminal activities targeting the IoMT devices, raising serious security and privacy concerns when healthcare professionals deal with sensitive and life-critical medical information. Machine learning has been recently applied in such data-driven IoMT applications when it comes to detecting network intrusions. In this tutorial, we introduce the data preprocessing and classification techniques using logistic regression, decision trees, support vector machines, and neural networks, and then their applications on a real-world dataset collected in an IoMT network for detecting man-in-the-middle attacks. The main objectives of this tutorial are to (1) understand supervised learning for classification and unsupervised learning for grouping, (2) build training and validation datasets using Python, (3) use JMP statistical tool to select significant features from the dataset step by step, (4) build machine learning-based predictive models using Python, these include logistic regression, decision trees (and random forest), support vector machines and neural networks, and (5) choose parameters and interpret results generated from these predictive models.

Table of Content:
1. Introduction to IoMT
2. Man-In-The-Middle Attack
3. IoMT Data Collection and Preprocessing
4. Feature Selection for Detecting Cyber Attacks in IoMT
5. Machine Learning with Selected Features Using Python
6. Comparative Studies on Machine Learning-Based Predictive Models
7. Conclusions

Contact Us: widecom2022@easychair.org