Modeling multivariate cyber risks : deep learning dating extreme value theory
© 2021 Informa UK Limited, trading as Taylor & Francis Group.
| Publié dans: | Journal of applied statistics. - 1991. - 50(2023), 3 vom: 23., Seite 610-630 |
|---|---|
| Auteur principal: | |
| Autres auteurs: | , , , |
| Format: | Article en ligne |
| Langue: | English |
| Publié: |
2023
|
| Accès à la collection: | Journal of applied statistics |
| Sujets: | Journal Article Cyber attacks GPD LSTM heavy tail high-dimensional dependence |
| Résumé: | © 2021 Informa UK Limited, trading as Taylor & Francis Group. Modeling cyber risks has been an important but challenging task in the domain of cyber security, which is mainly caused by 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 predictions via extreme value theory. Both the simulation and empirical studies show that the proposed approach can model the multivariate cyber risks very well and provide satisfactory prediction performances |
|---|---|
| Description: | Date Revised 24.02.2023 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
| ISSN: | 0266-4763 |
| DOI: | 10.1080/02664763.2021.1936468 |