Starling: security and resource allocation on B5G via artificial intelligence techniques

• Grant number: 21/06995-0
• Support Opportunities: Regular Research Grants
• Start date: August 01, 2023
• End date: July 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Agreement: MCTI/MC
• Principal Investigator: Daniel Macêdo Batista
• Grantee: Daniel Macêdo Batista
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated researchers: Michele Nogueira Lima ; Mosab Hamdan Adam Mohamed Alhassan ; Paulo Angelo Alves Resende ; Pedro Henrique Gomes da Silva ; Rodrigo Izidoro Tinini
• Associated scholarship(s): 24/09448-9 - Resource Allocation Guaranteeing Time Requirements for Smart Grids, BP.TT; 24/10240-3 - DDoS Detection in the Internet of Things using Machine Learning Methods with Retraining, BP.TT; 23/13638-5 - Performance evaluation of machine learning techniques in online classification of malicious traffic, BP.TT; 23/13669-8 - DDoS Detection in the Internet of Things using Machine Learning Methods with Retraining, BP.TT

Abstract

The shifts in mobile telecommunications infrastructure paradigms and capabilities brought with the fifth generation (5G) have heightened interest and anticipated the development of the next generations, identified as Beyond 5G (B5G). Massive Machine Type Communication (mMTC) and Ultra-Reliable and Low Latency Communication (URLLC) stand out as use cases for these next generations. Common to these use cases is the need to manage resources through network slicing and virtualization, the need for quick decision-making through Artificial Intelligence services, and the need to ensure network security taking into account the very high transmission rates. In this environment, applications such as smart cities and the Industrial Internet of Things will require innovative network solutions in order to function correctly with the necessary security. In this sense, this project presents four research lines related to improvements needed in various aspects of B5G to make the next generations of mobile telecommunications reliable, highly automated and with native support for Artificial Intelligence mechanisms. This project is related to the theme Internet-Enabler Technologies specified in the call for proposals. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

MOSAIYEBZADEH, FATEMEH; POURIYEH, SEYEDAMIN; HAN, MENG; LIU, LIYUAN; XIE, YIXIN; ZHAO, LIANG; BATISTA, DANIEL MACEDO. Privacy-Preserving Federated Learning-Based Intrusion Detection System for IoHT Devices. ELECTRONICS, v. 14, n. 1, p. 18-pg., 2025-01-01. (21/06995-0, 15/24485-9, 14/50937-1)

ANDRADE DE ARAUJO JOSEPHIK, JOAO GABRIEL; SIQUEIRA, YAISSA; MACHADO, KETLY GONCALVES; TERADA, ROUTO; DOS SANTOS, ALDRI LUIZ; NOGUEIRA, MICHELE; BATISTA, DANIEL MACEDO. Applying Hoeffding Tree Algorithms for Effective Stream Learning in IoT DDoS Detection. 2023 IEEE LATIN-AMERICAN CONFERENCE ON COMMUNICATIONS, LATINCOM, v. N/A, p. 6-pg., 2023-01-01. (18/23098-0, 15/24485-9, 21/06995-0, 14/50937-1)

BAZALUK, BRUNA; HAMDAN, MOSAB; GHALEB, MUSTAFA; GISMALLA, MOHAMMED S. M.; DA SILVA, FLAVIO S. CORREA; BATISTA, DANIEL MACEDO. Towards a Transformer-Based Pre-trained Model for IoT Traffic Classification. PROCEEDINGS OF 2024 IEEE/IFIP NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM, NOMS 2024, v. N/A, p. 7-pg., 2024-01-01. (15/24485-9, 21/06995-0, 14/50937-1)