Research theme
AI for Cybersecurity
AI that detects intrusions, malware and zero-day attacks before they reach hospitals, banks and homes.
-
Neural-Heatmap: Seeing Cyber Threats Across an Organisation at a Glance
Neural-Heatmap pairs a BiLSTM intrusion detector with a real-time risk heatmap, reaching 98.86% accuracy and cutting the time to find compromised zones by 89.82%.
-
Explainable, Real-Time Intrusion Prevention for 5G and Beyond
An explainable intrusion detection and prevention framework for 5G/6G and SDN networks reached over 94% accuracy, explained decisions in under 5 ms and cut response latency…
-
Malware Detection You Can Trust and Understand
A LightGBM malware detector with LIME and SHAP explanations and adversarial defences reached 91.16% accuracy and stayed robust under attack.