Abstract
The study of cybersecurity incidents is an active research field. The purpose of this work is to determine accurate measures of cybersecurity incidents. An effective method to aggregate cybersecurity incident reports is defined to set these measures. As a result we are able to make predictions and, therefore, to deploy security policies. Forecasting time-series of those cybersecurity aggregates is performed based on Koopman's method and Dynamic Mode Decomposition algorithm. Both techniques have shown to be accurate for a wide variety of dynamical systems ranging from fluid dynamics to social sciences. We have performed some experiments on public databases. We show that the measure of the risk trend can be effectively forecasted.
Highlights
Incidents of cybersecurity are ever-present threats compromising cybersystems
In the first set of experiments, we noticed how the best results were obtained with the third dictionary D3 for window size = 48 points and a training percentage of around 70%
This is a choice that is highly dependent on the data we are treating, so we suggest a fine-tuning of these parameters when considering applications of the method described in this article
Summary
Incidents of cybersecurity are ever-present threats compromising cybersystems. These events provoke social and economic losses by outwitting legitimate security systems. It is needed to detect, classify, and even predict these kinds of events to protect ourselves from damages they cause. Several works have studied cybersecurity incidents and threats from different perspectives; see [33], [40], and references therein. They focus on analysis, detection, and prevention, but no prediction schemes have been provided to set up proactive measures to avoid the damage in advance. The first problem one faces performing a predictive cybersecurity model is to define a cybersecurity threat. One needs to fix a concrete classification before setting up the model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
