Rafiqul Islam

The paper proposes a privacy-aware machine unlearning framework using SISA training to efficiently remove the influence of specific training data from RL-based ransomware detectors with minimal performance loss.

TL-RL-FusionNet is a novel reinforcement learning-guided framework that enhances ransomware detection by adaptively focusing on complex, evolving threats, achieving high accuracy and superior efficiency compared to static models.

The study assesses the generalization capability of supervised machine learning models for intrusion detection using UNSW-NB15 and TON_IoT, finding a significant performance drop when models are tested on unseen datasets.

DSTAN-Med is a novel dual-channel attention framework that significantly improves False Data Injection (FDI) attack detection in IoMT medical devices by explicitly separating spatial and temporal dependencies and incorporating physiological constraints.