@InProceedings{lim-EtAl:2017:Long,
  author    = {Lim, Swee Kiat  and  Muis, Aldrian Obaja  and  Lu, Wei  and  Ong, Chen Hui},
  title     = {MalwareTextDB: A Database for Annotated Malware Articles},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  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.},
  url       = {http://aclweb.org/anthology/P17-1143}
}