Adversarially Resilient Federated Learning for Intrusion Detection in 5G Networks

This project will design and test a new privacy-preserving, attack-resilient cybersecurity system for 5G networks using Federated Learning (FL), an approach where multiple devices can train models together without sharing sensitive data. The goal is to improve protection against cyberattacks such as denial-of-service and model poisoning, which threaten the reliability of modern mobile services like autonomous vehicles, industrial IoT, and virtual reality. By working together, the University of Northern British Columbia and City, University of London will combine their expertise in machine learning, cybersecurity, and distributed systems to create a secure framework that benefits both institutions. The collaboration will provide valuable training for students, strengthen international research ties, and contribute to practical tools that can enhance cybersecurity for Canadian and global industries.

Faculty Supervisor:

Sajal Saha

Student:

Partner:

St George's, University of London

Discipline:

Computer science

Sector:

Cyber Security

University:

University of Northern British Columbia

Program: