Listen carefully to what data whisper, or how I discovered new perspectives for cybersecurity systems
Title: Listen carefully to what data whisper, or how I discovered new perspectives for cybersecurity systems
Reports on the global cyber-security landscape prove that DDoS (Distributed Denial of Service) attacks are the dominant threat for the market of network services. The number of attacks is growing every year, and so is the scale and the complexity of attack dynamics.
There are already many DDoS detection and mitigation systems available. Most of them, though, use signature-based (supervised learning) mechanisms, comparing the content of network packets or statistical features of network flows with patterns of already known attacks.
The new patent-pending approach I will discuss does not need signatures to solve the attack detection and mitigation problem. It turned out that by asking the right questions about the structure and evolution of the network traffic data, I was able to handle even the multidimensional time-varying attacks in real-time, with no pre-knowledge available. Even more, this insight created new perspectives on how to address cybersecurity problems with tools that haven’t been considered for the job before.
Michał Karpowicz, PhD is an Assistant Professor of Computer Science and Head of IT Systems Engineering Department at NASK National Research Institute for Cybersecurity & AI. He received his B.S., M.S., and Ph.D. from the Institute of Control and Computation Engineering at the Warsaw University of Technology. His research interests include control theory, signal processing, and game theory.