| Title | Machine Learning Approach to Predict Computer Operating Systems Vulnerabilities |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Alenezi, Freeh, Tsokos, Chris P. |
| Conference Name | 2020 3rd International Conference on Computer Applications Information Security (ICCAIS) |
| Date Published | March 2020 |
| Publisher | IEEE |
| ISBN Number | 978-1-7281-4213-5 |
| Keywords | composability, computer, data mining, Databases, Linux, Linux operating system, Linux Operating System Security, machine leaning, Metrics, Microsoft Windows, operating system, Operating Systems Security, Predictive models, predictive security metrics, pubcrawl, resilience, Resiliency, security |
| Abstract | Information security is everyone's concern. Computer systems are used to store sensitive data. Any weakness in their reliability and security makes them vulnerable. The Common Vulnerability Scoring System (CVSS) is a commonly used scoring system, which helps in knowing the severity of a software vulnerability. In this research, we show the effectiveness of common machine learning algorithms in predicting the computer operating systems security using the published vulnerability data in Common Vulnerabilities and Exposures and National Vulnerability Database repositories. The Random Forest algorithm has the best performance, compared to other algorithms, in predicting the computer operating system vulnerability severity levels based on precision, recall, and F-measure evaluation metrics. In addition, a predictive model was developed to predict whether a newly discovered computer operating system vulnerability would allow attackers to cause denial of service to the subject system. |
| URL | https://ieeexplore.ieee.org/document/9096731 |
| DOI | 10.1109/ICCAIS48893.2020.9096731 |
| Citation Key | alenezi_machine_2020 |
Machine Learning Approach to Predict Computer Operating Systems Vulnerabilities