Cybersecurity Risk Assessment Using Graph Theoretical Anomaly Detection and Machine Learning

<p>The cyber domain is a great business enabler providing many types of enterprises new opportunities such as scaling up services, obtaining customer insights, identifying end-user profiles, sharing data, and expanding to new communities. However, the cyber domain also comes with its own set of risks. Cybersecurity risk assessment helps enterprises explore these new opportunities and, at the same time, proportionately manage the risks by establishing cyber situational awareness and identifying potential consequences. Anomaly detection is a mechanism to enable situational awareness in the cyber domain. However, anomaly detection also requires one of the most extensive sets of data and features for proper implementation. One way to make disparate data more usable is by using relations within datasets to provide more robust representations of interdependencies.</p> <p>The purpose of this study is to use machine learning classification algorithms augmented by a new feature set extracted with graph theoretical information representing human to human and human to machine interactions in the quantification of cyber risk due to insider threats. Included in this study is impact assessment by analyzing past incidents caused by internal actors and depicted on the risk matrices, together with datasets on organizational roles of the internal actors.</p>

Name thesis:degree_name

Doctor of Philosophy (PhD)

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Engineering Management & Systems Engineering

Year dc:date.available

2021

Author dc:creator

• Kucukkaya, Goksel

Contributors dc:contributor

• C. Ariel Pinto
• Adrian Gheorghe
• Mustafa Canan
• Saltuk Bugra Karahan

• Cybersecurity
• Risk assessment
• Anomaly detection
• Artificial Intelligence and Robotics
• Business Administration, Management, and Operations
• Information Security
• Risk Analysis
• Systems Engineering

Identifier

9798516059070

OAI identifier oai:identifier

oai:digitalcommons.odu.edu:emse_etds-1183