Secure cyber incident analytics framework using Monte Carlo simulations for financial cybersecurity insurance in cloud computing. (27th May 2016)

• Record Type: Journal Article
• Authors: Gai, Keke; Qiu, Meikang; Hassan, Houcine
• Other Names: Xiang Yang guestEditor.; Bertino Elisa guestEditor.; Kutylowski Miroslaw guestEditor.; Plessl Christian guestEditor.; Cong Guojing guestEditor.; Cardoso João M. P. guestEditor.
• Is Part Of: Concurrency and computation. Volume 29:Number 7(2017)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2016-05-27
• Subjects: Cybersecurity insurance -- incident analytics framework -- cloud computing -- Monte Carlo simulation -- information security -- financial industry; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.3856
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: The remarkable increasing demands of mitigating losses from cyber incidents for financial firms have been driving the rapid development of the Cybersecurity Insurance (CI). The implementations of CI have covered a variety of aspects in cyber incidents, from hacking to frauds. However, CI is still at its exploring stage so that there are a number of dimensions that are uncovered by the current applications. The cyber attack on critical infrastructure is one of the serious issues that prevents the expansions of CI. This paper addresses CI implementations focusing on cloud‐based service offerings and proposes a secure cyber incident analytics framework using big data, named as Cost‐Aware Hierarchical Cyber Incident Analytics (CA‐HCIA). The approach is designed for matching different cyber risk scenarios, which uses repository data. We use Monte Carlo simulations for extracting the incident features based on the training datasets. The main algorithms in CA‐HCIA include Monte Carlo Cyber Feature Extraction (MC2FE) and Optimal Cost Balance (OCA) Algorithms . Our experimental evaluation has provided the theoretical proof of the adoptability and feasibility. Results show that our proposal improves the cost of existing techniques in 7.98% and 15.39%. Copyright © 2016 John Wiley & Sons, Ltd.