Patrik is a research assistant and Ph.D. student at KInIT, doing his Ph.D. at the Faculty of Information Technology, Brno University of Technology. He specializes in computer networking and information system security using artificial intelligence and machine learning systems. Nevertheless, he believes that developing ever-increasing complex models does not bring huge improvements for the security domain anymore, and more focus should be put on other aspects, such as the data or model explainability. For this reason, he focuses on analyzing and determining the quality of network cybersecurity data, which he believes can help in achieving requirements for security solutions better.
Patrik obtained both his Bachelor’s and Master’s degrees from the Faculty of Information Technology, Brno University of Technology. During these studies, he was primarily focused on DDoS attack detection and mitigation as an R&D engineer in CESNET z.s.p.o. Both his Bachelor’s and Master’s theses discussed DDoS mitigation – the first using traditional and the latter utilizing machine learning techniques.
Besides network security, his other professional interests include data science, penetration testing, digital forensics, and parallel algorithms. When not saving the World from cyber-attacks, Patrik likes to enjoy good quality tea, Yerba maté, ceremonial cacao, or essentially any non-alcoholic drink with a great taste and the potential to boost one’s mood and mind. Patrik embraces lifelong learning, visiting various events, talks, listening to podcasts, and reading non-fiction books to broaden his horizons to be better today than the day before.
PhD topic: Data-centric AI for Network Intrusion Detection
Supervising team: Daniela Chudá (KInIT)
Nowadays, many types of cyberattacks aiming to compromise information systems exist in-the-wild. In order to protect information and communication infrastructure, these attacks must be detected and prevented from succeeding. Such goals are typically achieved by Intrusion Detection Systems (IDSs), which monitor the target system or a network and alert on potential malicious or anomalous behavior. Our research focuses on the domain of network intrusion detection using machine learning (ML). ML utilization has greatly improved attack detection capabilities and made the systems significantly more flexible. However, machine learning is heavily dependent on the data, which is one of the main issues within the domain currently. In order to address the data problem, our research aims to pursue the three areas of interest built around the data-centric artificial intelligence approach. Research efforts will be focused on data augmentation, feature engineering, and transfer learning. By achieving these preset research goals, we believe that ML-based IDSs will become more robust by training on higher-quality data and, thus, be more viable for real-world usage.