<?xml version="1.0"?>

<!DOCTYPE owl [
	<!ENTITY rdf "http://www.w3.org/1999/02/22-rdf-syntax-ns#">
	<!ENTITY rdfs "http://www.w3.org/2000/01/rdf-schema#">
	<!ENTITY xsd "http://www.w3.org/2001/XMLSchema#">
	<!ENTITY owl "http://www.w3.org/2002/07/owl#">
	<!ENTITY cc "http://web.resource.org/cc/#">
	<!ENTITY project "http://ebiquity.umbc.edu/ontology/project.owl#">
	<!ENTITY person "http://ebiquity.umbc.edu/ontology/person.owl#">
	<!ENTITY pub "http://ebiquity.umbc.edu/ontology/publication.owl#">
	<!ENTITY assert "http://ebiquity.umbc.edu/ontology/assertion.owl#">
]>

<!--

This ontology document is licensed under the Creative Commons
Attribution License. To view a copy of this license, visit
http://creativecommons.org/licenses/by/2.0/ or send a letter to
Creative Commons, 559 Nathan Abbott Way, Stanford, California
94305, USA.

-->

<rdf:RDF 
		xmlns:rdf = "&rdf;"
		xmlns:rdfs = "&rdfs;"
		xmlns:xsd = "&xsd;"
		xmlns:owl = "&owl;"
		xmlns:cc = "&cc;"
		xmlns:project = "&project;"
		xmlns:person = "&person;"
		xmlns:pub = "&pub;"
		xmlns:assert = "&assert;">
	<pub:InProceedings rdf:about="http://ebiquity.umbc.edu/paper/html/id/999/CyBERT-Contextualized-Embeddings-for-the-Cybersecurity-Domain">
		<rdfs:label><![CDATA[CyBERT: Contextualized Embeddings for the Cybersecurity Domain]]></rdfs:label>
		<pub:title><![CDATA[CyBERT: Contextualized Embeddings for the Cybersecurity Domain]]></pub:title>
		<pub:publishedOn rdf:datatype="&xsd;dateTime">2021-12-15T00:00:00-05:00</pub:publishedOn>
		<pub:abstract><![CDATA[We present CyBERT, a domain-specific Bidirectional Encoder Representations from Transformers (BERT) model, fine-tuned with a large corpus of textual cybersecurity data. State-of-the-art natural language models that can process dense, fine-grained textual threat, attack, and vulnerability information can provide numerous benefits to the cybersecurity community. The primary contribution of this paper is to provide the security community with an initial fine-tuned BERT model that can perform a variety of cybersecurity-specific downstream tasks with high accuracy and efficient use of resources. We create a cybersecurity corpus from open-source unstructured and semi-unstructured Cyber Threat Intelligence (CTI) data and use it to fine-tune a base BERT model with Masked Language Modeling (MLM) to recognize specialized cybersecurity entities. We evaluate the model using various downstream tasks that can benefit modern Security Operations Centers (SOCs). The fine-tuned CyBERT model outperforms the base BERT model in the domain-specific MLM evaluation. We also provide use cases of CyBERT applications in cybersecurity-based downstream tasks.

<p> This material is based upon work supported by a grant from the NSA and from NSF Grant No. 2114892. </p>

<meta name="twitter:card" content="summary_large_image">
<meta name="twitter:site" content="@ebiquity">
<meta name="twitter:creator" content="@ebiquity" />
<meta property="og:image" content="https://ebiquity.umbc.edu/blogger/wp-content/uploads/2021/11/cybert.png"/>
<meta property="og:url" content="https://ebiquity.umbc.edu/paper/html/id/999/CyBERT-Contextualized-Embeddings-for-the-Cybersecurity-Domain" />
<meta property="og:title" content="CyBERT: Contextualized Embeddings for the Cybersecurity Domain" />
<meta property="og:description" content="New paper on CyBERT, a domain-specific Bidirectional Encoder Representations from Transformers (BERT) model, fine-tuned with a large corpus of textual cybersecurity data. #AI #LLM #BERT #cyberSecurity" />
<meta name="twitter:image" content="https://ebiquity.umbc.edu/blogger/wp-content/uploads/2021/11/cybert.png">]]></pub:abstract>
		<pub:pages><![CDATA[3334-3342]]></pub:pages>
		<pub:note><![CDATA[DOI: <a href="https://doi.org/10.1109/BigData52589.2021.9671824">10.1109/BigData52589.2021.9671824</a>
<p><img src="https://i.imgur.com/Cur2HQR.png" style="display: block; margin-left: auto; margin-right: auto; max-width: 100%; height: auto;"><p>
<meta name="twitter:image" content="https://ebiquity.umbc.edu/blogger/wp-content/uploads/2021/11/cybert.png">]]></pub:note>
		<pub:organization><![CDATA[IEEE]]></pub:organization>
		<pub:counter>3268</pub:counter>
		<pub:tag><![CDATA[ai]]></pub:tag>
		<pub:tag><![CDATA[bert]]></pub:tag>
		<pub:tag><![CDATA[cti]]></pub:tag>
		<pub:tag><![CDATA[cyber threat intelligence]]></pub:tag>
		<pub:tag><![CDATA[cybersecurity]]></pub:tag>
		<pub:tag><![CDATA[cybert]]></pub:tag>
		<pub:tag><![CDATA[embedding]]></pub:tag>
		<pub:tag><![CDATA[llm]]></pub:tag>
		<pub:tag><![CDATA[natural language processing]]></pub:tag>
		<pub:booktitle><![CDATA[IEEE International Conference on Big Data]]></pub:booktitle>
		<pub:publisher><![CDATA[IEEE]]></pub:publisher>
		<pub:author>
			<rdf:List>
				<rdf:first>
					<person:Person rdf:about="http://ebiquity.umbc.edu/person/html/Anupam/Joshi"><person:name><![CDATA[Anupam Joshi]]></person:name><rdfs:label><![CDATA[Anupam Joshi]]></rdfs:label></person:Person>
				</rdf:first>
				<rdf:rest>					<rdf:List>
						<rdf:first>
							<person:Person rdf:about="http://ebiquity.umbc.edu/person/html/Tim/Finin"><person:name><![CDATA[Tim Finin]]></person:name><rdfs:label><![CDATA[Tim Finin]]></rdfs:label></person:Person>
						</rdf:first>
						<rdf:rest>							<rdf:List>
								<rdf:first>
									<person:Person rdf:about="http://ebiquity.umbc.edu/person/html/Priyanka/Ranade"><person:name><![CDATA[Priyanka Ranade]]></person:name><rdfs:label><![CDATA[Priyanka Ranade]]></rdfs:label></person:Person>
								</rdf:first>
								<rdf:rest>									<rdf:List>
										<rdf:first>
											<person:Person rdf:about="http://ebiquity.umbc.edu/person/html/Aritran/Piplai"><person:name><![CDATA[Aritran Piplai]]></person:name><rdfs:label><![CDATA[Aritran Piplai]]></rdfs:label></person:Person>
										</rdf:first>
										<rdf:rest rdf:resource="&rdf;nil" />
									</rdf:List>
								</rdf:rest>
							</rdf:List>
						</rdf:rest>
					</rdf:List>
				</rdf:rest>
			</rdf:List>
		</pub:author>
		<pub:firstAuthor>
<person:Person rdf:about="http://ebiquity.umbc.edu/person/html/Anupam/Joshi"><person:name><![CDATA[Anupam Joshi]]></person:name><rdfs:label><![CDATA[Anupam Joshi]]></rdfs:label></person:Person>
		</pub:firstAuthor>
		<pub:softCopy><pub:SoftCopy>
			<pub:softCopyFormat><![CDATA[PDF Document]]></pub:softCopyFormat>
			<pub:softCopyURI><![CDATA[http://ebiquity.umbc.edu/get/a/publication/1188.pdf]]></pub:softCopyURI>
			<pub:softCopySize>1030673</pub:softCopySize>
			</pub:SoftCopy>
			</pub:softCopy>
	</pub:InProceedings>

<rdf:Description rdf:about="">
	<cc:License rdf:resource="http://creativecommons.org/licenses/by/2.0/" />
</rdf:Description>

</rdf:RDF>
