@inproceedings{lim-etal-2017-malwaretextdb,
title = "{M}alware{T}ext{DB}: A Database for Annotated Malware Articles",
author = "Lim, Swee Kiat and
Muis, Aldrian Obaja and
Lu, Wei and
Ong, Chen Hui",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1143",
doi = "10.18653/v1/P17-1143",
pages = "1557--1567",
abstract = "Cybersecurity risks and malware threats are becoming increasingly dangerous and common. Despite the severity of the problem, there has been few NLP efforts focused on tackling cybersecurity. In this paper, we discuss the construction of a new database for annotated malware texts. An annotation framework is introduced based on the MAEC vocabulary for defining malware characteristics, along with a database consisting of 39 annotated APT reports with a total of 6,819 sentences. We also use the database to construct models that can potentially help cybersecurity researchers in their data collection and analytics efforts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lim-etal-2017-malwaretextdb">
<titleInfo>
<title>MalwareTextDB: A Database for Annotated Malware Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swee</namePart>
<namePart type="given">Kiat</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aldrian</namePart>
<namePart type="given">Obaja</namePart>
<namePart type="family">Muis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="given">Hui</namePart>
<namePart type="family">Ong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cybersecurity risks and malware threats are becoming increasingly dangerous and common. Despite the severity of the problem, there has been few NLP efforts focused on tackling cybersecurity. In this paper, we discuss the construction of a new database for annotated malware texts. An annotation framework is introduced based on the MAEC vocabulary for defining malware characteristics, along with a database consisting of 39 annotated APT reports with a total of 6,819 sentences. We also use the database to construct models that can potentially help cybersecurity researchers in their data collection and analytics efforts.</abstract>
<identifier type="citekey">lim-etal-2017-malwaretextdb</identifier>
<identifier type="doi">10.18653/v1/P17-1143</identifier>
<location>
<url>https://aclanthology.org/P17-1143</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>1557</start>
<end>1567</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MalwareTextDB: A Database for Annotated Malware Articles
%A Lim, Swee Kiat
%A Muis, Aldrian Obaja
%A Lu, Wei
%A Ong, Chen Hui
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F lim-etal-2017-malwaretextdb
%X Cybersecurity risks and malware threats are becoming increasingly dangerous and common. Despite the severity of the problem, there has been few NLP efforts focused on tackling cybersecurity. In this paper, we discuss the construction of a new database for annotated malware texts. An annotation framework is introduced based on the MAEC vocabulary for defining malware characteristics, along with a database consisting of 39 annotated APT reports with a total of 6,819 sentences. We also use the database to construct models that can potentially help cybersecurity researchers in their data collection and analytics efforts.
%R 10.18653/v1/P17-1143
%U https://aclanthology.org/P17-1143
%U https://doi.org/10.18653/v1/P17-1143
%P 1557-1567
Markdown (Informal)
[MalwareTextDB: A Database for Annotated Malware Articles](https://aclanthology.org/P17-1143) (Lim et al., ACL 2017)
ACL
- Swee Kiat Lim, Aldrian Obaja Muis, Wei Lu, and Chen Hui Ong. 2017. MalwareTextDB: A Database for Annotated Malware Articles. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1557–1567, Vancouver, Canada. Association for Computational Linguistics.