| Abstract: | Cybersecurity has the utmost importance for nuclear power plants (NPPs). Demand for clean and constant energy has increased the need and use of NPPs. Countries want to have and maintain secure NPPs both physically (well-studied area) and digitally. We live in a digital world, and cyber-attacks have skyrocketed in recent years. This study explores the cyber risk for NPPs, digital attacks, potential future attacks, international aspects, and law and policy requirements of cyber protection for nuclear power plants. With the help of data analysis and machine learning algorithms, extra monitoring can be conducted on plants' data. Data monitoring applications require comprehensive data to build models and develop solutions. However, nuclear facilities do not share their data because of security concerns. Plant simulators are heavily used for training people and conducting experiments. In this thesis, we inspect plant simulators to assess their usability by people with a technical background such as cyber experts, information technology technicians, and software developers. People responsible for protecting digital systems can benefit from the help of data analytic tools and machine learning models to detect abnormalities. We study machine learning models on simulator data to examine their potential in identifying anomalies. The electronic version of this dissertation is accessible from https://hdl.handle.net/1969.1/197764 |
|---|