Research theme
AI for Cybersecurity
AI that detects intrusions, malware and zero-day attacks before they reach hospitals, banks and homes.
-
Securing the Unseen: Can AI Catch Cyberattacks Nobody Has Seen Before?
A systematic review of four AI model families for detecting zero-day cyberattacks, comparing accuracy, calibration, speed and how well they handle truly unknown threats.
-
BankNet: Real-Time AI That Detects Online Banking Fraud
BankNet combines big data tools with a BiLSTM neural network to analyse internet banking transactions in real time, detecting fraud with 98.5% accuracy.
-
Hiding Secret Messages Inside Images, Securely
A three-layer method hides encrypted messages inside ordinary images using AES encryption, XOR and DCT-based steganography, keeping image quality high and decoding error-free.