Options
Predicting vulnerable software components via text mining
Publikationstyp
Journal Article
Date Issued
2014-10-01
Sprache
English
Volume
40
Issue
10
Start Page
993
End Page
1006
Article Number
6860243
Citation
IEEE Transactions on Software Engineering 40 (10): 6860243, 993-1006 (2014-10-01)
Publisher DOI
Scopus ID
Publisher
IEEE
This paper presents an approach based on machine learning to predict which components of a software application contain security vulnerabilities. The approach is based on text mining the source code of the components. Namely, each component is characterized as a series of terms contained in its source code, with the associated frequencies. These features are used to forecast whether each component is likely to contain vulnerabilities. In an exploratory validation with 20 Android applications, we discovered that a dependable prediction model can be built. Such model could be useful to prioritize the validation activities, e.g., to identify the components needing special scrutiny.
Subjects
machine learning
prediction model
Vulnerabilities
MLE@TUHH
DDC Class
004: Informatik