Institutional Repository of Vilnius University
Kibernetiniai pažeidžiamumai ir jų tyrimas /
Abstract
dc:descriptionIn recent years, cybersecurity field has been evolving rapidly, with vulnerability management becoming one of the key problems of organizational defense. Traditional methods of vulnerability assessment often rely on static metrics such as the Common Vulnerability Scoring System (CVSS). However, this metric does not always accurately depict the real-world risk or likelihood of vulnerability exploitation. A vulnerability with a high CVSS score might never be exploited in practice, while another with a lower score might be actively targeted by attacks. This thesis aims to develop an intelligent vulnerability analysis module which would be capable to automatically collect vulnerability related data from multiple trusted sources, such as the National Vulnerability Database (NVD). The collected information would include factors like patch availability, public exploit existence, exposure level, and publication timestamps. The goal is to build a dataset that shows both technical and contextual aspects of vulnerabilities and to use machine learning techniques to dynamically prioritize them based on real life risk potential. The research focuses on integrating automated scanning with external data enrichment through API-based lookups and parsing mechanisms. The system will collect CVE identifiers using network scanning tools such as Nmap with vulnerability scripts and enrich these findings with real-time intelligence from NVD and other security databases. Once collected, the data will be preprocessed and used to train a machine learning model to predict the priority of each vulnerability, taking into account the probability of exploitation.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Lipskis, Martynas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD277689853&prefLang=en_US