Linking Common Vulnerabilities and Exposures to the MITRE ATT&CK Framework: A Self-Distillation Approach

Benjamin M. Ampel, Sagar Samtani, Steven Ullman, Hsinchun Chen
Last updated on Jun 9, 2026
PDF DOI
In Plain Terms

This paper bridges two separate cybersecurity resources: the CVE list of known software vulnerabilities and the MITRE ATT&CK framework of attacker tactics and defenses. The authors build a language model called CVET that automatically tags each vulnerability with one of ten ATT&CK tactics, using a self-distillation technique on top of RoBERTa. This lets security teams quickly attach likely mitigation context to the vulnerabilities they track.

Artifacts

PDF DOI

Related Papers

Cite this

APA Ampel, B. M., Samtani, S., Ullman, S., & Chen, H. (2021). Linking Common Vulnerabilities and Exposures to the MITRE ATT&CK Framework: A Self-Distillation Approach. In ACM KDD Workshop on AI-enabled Cybersecurity Analytics. https://doi.org/10.48550/arXiv.2108.01696
BibTeX
@inproceedings{ampel2021linking,
  title={Linking Common Vulnerabilities and Exposures to the MITRE ATT&CK Framework: A Self-Distillation Approach},
  author={Benjamin M. Ampel and Sagar Samtani and Steven Ullman and Hsinchun Chen},
  booktitle={ACM KDD Workshop on AI-enabled Cybersecurity Analytics},
  year={2021},
  doi={10.48550/arXiv.2108.01696}
}
CVE MITRE ATT&CK Deep Learning Self-Distillation Vulnerability Assessment
Benjamin M. Ampel

Benjamin M. Ampel

Assistant Professor in Computer Information Systems and Director, Center for CyberAI Research (CCAIR)

My research focuses on AI-enabled Cybersecurity, including Cyber Threat Intelligence, Large Language Models, and Phishing Detection.