At present, IQSeC Lab has three research directions -- ML and Endpoint Security, ML and Network Security, and Quantum Security.
In this area, we investigate continual learning (CL) for ever-evolving and intelligent malware classification and detection systems. Our proposed state-of-the-art (SOTA) CL techniques enable these systems to adopt sequential learning, accommodating the constant influx of new malware types and shifts in data distribution.
In this research, we investigate advanced ML methods to uncover vulnerabilities in the leaked side-channel information of encrypted network traffic, such as Tor. Beyond merely identifying these vulnerabilities, we design SOTA attacks to exploit them and propose SOTA techniques to counteract existing and potential threats, thereby protecting users' online privacy.
In this research, we investigate the post-quantum vulnerabilities in the existing communication and network systems. Furthermore, we propose novel quantum-secure solutions based on quantum key distribution (QKD) and post-quantum cryptography (PQC) for the post-quantum era.
A preferred prospective PhD student will hold a bachelor's degree in Computer Science, Software Engineering, Computer Engineering, Electrical Engineering, or a related field. The candidate should have a strong inclination and intrinsic motivation to pursue research in machine learning and cybersecurity, and possess at least three of the preferred skills or experiences. Note that your goal should be to become a strong and mostly independent researcher, and my goal is to make sure you have the right set of resources to accomplish that goal.