Investigating the intersection of artificial intelligence and cyber security, with a focus on privacy-preserving distributed learning and smart critical infrastructure protection.
Privacy-preserving distributed machine learning for collaborative intrusion detection across heterogeneous IoT and IIoT networks. Research focuses on removing the need to centralise sensitive operational data while maintaining detection performance.
Intelligent intrusion detection systems for Industrial Internet of Things environments. Work addresses the challenges of class imbalance in attack datasets, adversarial threats, and deployment constraints of lightweight detection on edge devices.
Application of deep learning, adversarial machine learning, and generative AI to botnet detection, malware classification, and threat intelligence. Includes work on SMOTE-augmented training and recurrent architectures for sequential network traffic.
AI-based platforms for detecting cyberattacks on national energy systems. Active projects span smart grid security, windfarm protection, and SCADA monitoring. Funded under Innovate UK Cyber ASAP in partnership with industry.
Digital forensics methodologies, network forensics, evidence acquisition, and investigation techniques for cyber incident response. Informs the MSc and BSc curriculum on practical forensic investigation.
Secure mobility management in next-generation 6G networks, radio propagation modelling using neural networks, and AI-driven optimisation for future wireless systems. Early-career foundations in ANFIS and extreme learning machine models for path loss prediction.
Rural Environmental Monitoring via Ultra Wide-Area Networks and Distributed Federated Learning. Dr. Popoola serves as Federated Learning Specialist on this European Research Executive Agency Horizon Europe Staff Exchanges project.