Modeling Multivariate Cyber Risks: Deep Learning Dating Extreme Value Theory

03/15/2021
by   Mingyue Zhang Wu, et al.
0

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.

READ FULL TEXT

page 3

page 13

page 17

research
09/15/2022

Statistical Modeling of Data Breach Risks: Time to Identification and Notification

It is very challenging to predict the cost of a cyber incident owing to ...
research
01/19/2017

Extreme value statistics for censored data with heavy tails under competing risks

This paper addresses the problem of estimating, in the presence of rando...
research
06/19/2023

A VAE Approach to Sample Multivariate Extremes

Generating accurate extremes from an observational data set is crucial w...
research
05/04/2021

Aggregate Cyber-Risk Management in the IoT Age: Cautionary Statistics for (Re)Insurers and Likes

In this paper, we provide (i) a rigorous general theory to elicit condit...
research
01/14/2020

Scoring Predictions at Extreme Quantiles

Prediction of quantiles at extreme tails is of interest in numerous appl...
research
06/15/2023

Spatial modeling of extremes and an angular component

Many environmental processes such as rainfall, wind or snowfall are inhe...
research
05/24/2023

Model evaluation for extreme risks

Current approaches to building general-purpose AI systems tend to produc...

Please sign up or login with your details

Forgot password? Click here to reset