2026-09-18T22:59:25Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1432572022-06-16T03:58:59Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Hemberg, Erik
O’Reilly, Una-May
Srinivasan, Ashwin
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-06-15T13:07:45Z
2022-06-15T13:07:45Z
2022-02
2022-02-22T18:32:22.305Z
https://hdl.handle.net/1721.1/143257
Machine learning and natural language processing (NLP) can help describe and make inferences on the vast amount of text data in cybersecurity. We use a graph database named BRON, which contains data from publicly available threat and vulnerability sources, for machine learning inference. Applying machine learning to BRON can provide us with more robust relationships, which can improve defenses against cyber threats. We experiment with different feature representations and subsets of the data, and show that machine learning and NLP can effectively classify edges between entries from different data sources as well as predict possible edge candidates. Experts agree that several of our predicted candidates are plausible edges. We also analyze defensive mitigation similarities using NLP techniques and find that there are identical mitigation descriptions for some entries that have internal relationships.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Using Machine Learning for Description and Inference of Cyber Threats, Vulnerabilities, and Mitigations
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="06358e35-2e43-4985-ad61-5a66e166683c">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Using Machine Learning for Description and Inference of Cyber Threats, Vulnerabilities, and Mitigations</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-02</PublicationDate>
<Authors>
<Author>
<DisplayName>Srinivasan, Ashwin</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Machine learning and natural language processing (NLP) can help describe and make inferences on the vast amount of text data in cybersecurity. We use a graph database named BRON, which contains data from publicly available threat and vulnerability sources, for machine learning inference. Applying machine learning to BRON can provide us with more robust relationships, which can improve defenses against cyber threats. We experiment with different feature representations and subsets of the data, and show that machine learning and NLP can effectively classify edges between entries from different data sources as well as predict possible edge candidates. Experts agree that several of our predicted candidates are plausible edges. We also analyze defensive mitigation similarities using NLP techniques and find that there are identical mitigation descriptions for some entries that have internal relationships.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>