IEEE Transactions on Software Engineering · 2014 · 337 citations · 33 references
ComputingComputer ScienceCybersecurityMachine LearningSoftware EngineeringVulnerability AnalysisMobile Application VulnerabilitiesSoftware Security EngineeringSoftware Vulnerability DiscoveryVulnerability ManagementAndroid Application AnalysisMachine Learning For Vulnerability DetectionPrediction Model DevelopmentSoftware ComponentsSource Code Vulnerability AnalysisText Mining FeaturesVulnerability ForecastingVulnerability Prediction
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.
33
A few useful things to know about machine learning
Pedro Domingos · Communications of the ACM · 2012 · 3.2K citations
The Lack of A Priori Distinctions Between Learning Algorithms
David H. Wolpert · Neural Computation · 1996 · 1.6K citations