University of Twente Student Theses

Login

A Bayesian Network Model for predicting data breaches caused by insiders of a health care organization

Wilde, Lisa de (2016) A Bayesian Network Model for predicting data breaches caused by insiders of a health care organization.

[img] PDF
5MB
Abstract:In the Netherlands organizations are required by law to protect personal data. Since January 2016 they are also required to report breaches of security leading to (a considerable likelihood of) serious adverse effects on the protection of personal data to the Dutch data protection authority. In the health care sector medical data, which is extra sensitive, is processed and therefore security is even more important. Data breaches are, in this sector, mostly caused by insiders who have malicious intentions or make mistakes. For organizations it is hard to protect themselves effectively against insider threats and make sure that data breaches do not occur. To help organizations determine whether a data breach is likely to occur Bayesian networks can be used. During this research a model has been developed that combines prior indicators of a data breach and measures taken by an organization to predict the probability of a data breach in a health care. The model combines malicious and accidental insider threats posed by a group of insiders. When changing the observations the best combination of measures to minimize the probability of a data breach given certain prior indicators can be identified. Dataset: http://dx.doi.org/10.4121/uuid:c637245d-93fb-4cee-8f4a-9b5fa14d5513
Item Type:Essay (Master)
Clients:
KPMG, The Netherlands
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science MSc (60300)
Link to this item:https://purl.utwente.nl/essays/71534
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page