Automatic Labeling for Entity Extraction in Cyber Security
Abstract
Timely analysis of cyber-security information necessitates automated information extraction from unstructured text. While state-of-the-art extraction methods produce extremely accurate results, they require ample training data, which is generally unavailable for specialized applications, such as detecting security related entities; moreover, manual annotation of corpora is very costly and often not a viable solution. In response, we develop a very precise method to automatically label text from several data sources by leveraging related, domain-specific, structured data and provide public access to a corpus annotated with cyber-security entities. Next, we implement a Maximum Entropy Model trained with the average perceptron on a portion of our corpus (~750,000 words) and achieve near perfect precision, recall, and accuracy, with training times under 17 seconds.
- Authors:
-
- ORNL
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- Work for Others (WFO)
- OSTI Identifier:
- 1143555
- DOE Contract Number:
- DE-AC05-00OR22725
- Resource Type:
- Conference
- Resource Relation:
- Conference: 2014 ASE International Conference on Cyber Security, Stanford, CA, USA, 20140527, 20140331
- Country of Publication:
- United States
- Language:
- English
- Subject:
- Entity Extraction; Automatic Labeling; Maximum Entropy Model; Averaged Perceptron; Cyber Security
Citation Formats
Bridges, Robert A, Jones, Corinne L, Iannacone, Michael D, Testa, Kelly M, and Goodall, John R. Automatic Labeling for Entity Extraction in Cyber Security. United States: N. p., 2014.
Web.
Bridges, Robert A, Jones, Corinne L, Iannacone, Michael D, Testa, Kelly M, & Goodall, John R. Automatic Labeling for Entity Extraction in Cyber Security. United States.
Bridges, Robert A, Jones, Corinne L, Iannacone, Michael D, Testa, Kelly M, and Goodall, John R. 2014.
"Automatic Labeling for Entity Extraction in Cyber Security". United States.
@article{osti_1143555,
title = {Automatic Labeling for Entity Extraction in Cyber Security},
author = {Bridges, Robert A and Jones, Corinne L and Iannacone, Michael D and Testa, Kelly M and Goodall, John R},
abstractNote = {Timely analysis of cyber-security information necessitates automated information extraction from unstructured text. While state-of-the-art extraction methods produce extremely accurate results, they require ample training data, which is generally unavailable for specialized applications, such as detecting security related entities; moreover, manual annotation of corpora is very costly and often not a viable solution. In response, we develop a very precise method to automatically label text from several data sources by leveraging related, domain-specific, structured data and provide public access to a corpus annotated with cyber-security entities. Next, we implement a Maximum Entropy Model trained with the average perceptron on a portion of our corpus (~750,000 words) and achieve near perfect precision, recall, and accuracy, with training times under 17 seconds.},
doi = {},
url = {https://www.osti.gov/biblio/1143555},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Wed Jan 01 00:00:00 EST 2014},
month = {Wed Jan 01 00:00:00 EST 2014}
}