Manually annotated dataset reveals vulnerabilities in 5G networks, aiding security analysis and detection tools.
We present a manually annotated dataset, based on the National Vulnerability Database (NVD) from the National Institute of Standards and Technology (NIST), to assess different categories of vulnerabilities published from January 1, 2019, to July 1, 2025, for 5G networks and related technological infrastructures. We start by using keyword filtering to identify potentially relevant Common Vulnerabilities and Exposures (CVEs) related to 5G. Automated clustering is then applied to group semantically similar CVEs. Lastly, domain experts conduct a manual review, classifying vulnerabilities while verifying accuracy and maintaining consistency. The final dataset contains 1,531 CVEs classified into four categories: vulnerabilities inherited from legacy LTE technologies, those unique to 5G, those affecting both general ICT and 5G infrastructures, and those mistakenly linked to 5G technology. This dataset enables security researchers and network operators to analyze the 5G security landscape, where many technologies coexist. The annotated vulnerabilities support targeted assessment strategies and provide structured data for training automated 5G vulnerability detection tools.
No takes yet. Share an insight, caveat, or question.
D'Alterio et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: