Predictive Model for Cyber Attacks to Assess Financial Exposure for IoHT / IoMT

Cybersecurity incidents for Internet of Health Things (IoHT) and Internet of Medical Things (IoMT) organizations are rising. The Common Vulnerability Score System (CVSS) provides a system for both the prioritization and assessment of the impact of vulnerabilities on an organization. Vulnerability descriptions are provided to a vulnerability database where the issues are analyzed and assigned a score. Those scores can then assess a vulnerability's severity and priority. The problem is that these scores are subjective depending on the entity/individual who evaluates the exposure. This thesis aims to provide a predictive model to IoHT/IoMT leaders to assess the financial impact of cyber-attacks on their perspective organizations; this impact is determined using a combination of CVSS scores and the number of financial records impacted. Natural language processing (NLP) algorithms can help automate vulnerability severity score predictions based on textual descriptions provided by end users. NLP is helpful because it allows machines to process, analyze, and understand human language, which is essential for ensuring reproducibility. Automated prediction simplifies the process of assigning severity scores to vulnerabilities. Organizations can save time and resources by using NLP for this purpose. It will allow organizations to address and prioritize vulnerabilities promptly.Keywords: CVSS, IoHT, IoMT, BERT, Cyber Security, NLP, Financial Impact

Author

• Sanders, Apache Meyanna

Language

• en

Keyword

• BERT
• Cyber Security
• CVSS
• NLP

Date created

• 2023

Type of Work

• Dissertation

License

• All rights reserved

Rights statement

• In Copyright

GW Unit

• Engineering Management

Degree

• D.Engr.

Advisor

• Goodman, Joel

Committee Member(s)

• Blackford, JP
• Stirgwolt, Benjamin

Persistent URL

•  https://scholarspace.library.gwu.edu/etd/zs25x930p