Modeling Multivariate Cyber Risks: Deep Learning Dating Extreme Value Theory
This work addresses the problem of accurate cyber risk modeling for cybersecurity practitioners, though it appears incremental as it integrates existing methods.
The authors tackled the challenge of modeling multivariate cyber risks, which are high-dimensional and heavy-tailed, by combining deep learning with extreme value theory, achieving satisfactory prediction performances in both simulation and real-world honeypot attack data.
Modeling cyber risks has been an important but challenging task in the domain of cyber security. It is mainly because of the high dimensionality and heavy tails of risk patterns. Those obstacles have hindered the development of statistical modeling of the multivariate cyber risks. In this work, we propose a novel approach for modeling the multivariate cyber risks which relies on the deep learning and extreme value theory. The proposed model not only enjoys the high accurate point predictions via deep learning but also can provide the satisfactory high quantile prediction via extreme value theory. The simulation study shows that the proposed model can model the multivariate cyber risks very well and provide satisfactory prediction performances. The empirical evidence based on real honeypot attack data also shows that the proposed model has very satisfactory prediction performances.