Rahul is currently exploring the Cybersecurity domain, where he is designing and developing an ultra-low-energy Intrusion Detection System (IDS) for next-generation Internet of Medical Things (IoMT) security to transform global healthcare by enabling seamless connectivity among medical devices, systems, and services. An IDS is employed to monitor and protect systems or networks from unauthorised access, thereby ensuring the security of patient data and maintaining patient safety. It safeguards systems against hackers, cyberattackers, and other malicious threats by identifying intrusions and suspicious activities within systems and networks, and promptly notifying administrators so that appropriate actions can be taken. To develop the IDS, a new logic-based Machine Learning (ML) technique, namely, the Tsetlin Machine (TM), is employed. The TM is a novel and innovative ML technology- a better alternative to conventional AI. It represents a fundamental shift from arithmetic-based learning in conventional AI models to logic-based learning, enabling energy-efficient, faster-to-train, transparent, and easy-to-interpret AI models. Moreover, the IDS integrates cyber-resilient training and covert communication mechanisms to safeguard itself against various forms of adversarial attacks.
Rahul completed a Doctor of Philosophy (PhD) in Information and Communication Technology (ICT), with a specialization in Artificial Intelligence (AI), from the University of Agder (UiA), Norway. He received funding from the Research Council of Norway (RCN). During his doctoral studies, he developed AI-driven solutions, particularly using Transfer learning, to enhance the performance of next-generation wireless networks while relying on minimal sensor measurement data. His work enables system and network operators to improve end-user Quality of Experience (QoE) through intelligent network planning and more efficient utilization of available resources.
Before joining UiA, he was awarded a Master of Science (Research) by the School of Computer Science at University College Dublin (UCD), Dublin, Ireland. He received funding from the Science Foundation Ireland (SFI). During his master’s studies, he extensively worked with Data Science and Artificial Intelligence tools, with a particular focus on machine learning and deep learning, to design and develop novel no-reference speech quality prediction models for real-time monitoring of end-user speech quality across various VoIP applications, including WhatsApp, Google Meet, and Apple FaceTime.