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.

No abstract

Early identification of software vulnerabilities is essential in software engineering and can help reduce not only costs, but also prevent loss of reputation and damaging litigations for a software firm. Techniques and tools for software vulnerability prediction are thus invaluable. Most of the existing techniques rely on using component characteristic(s) (like code complexity, code churn) for the vulnerability prediction. In this position paper, we present a novel approach for vulnerability prediction that leverages on the analysis of raw source code as text, instead of using "cooked" features. Our initial results seem to be very promising as the prediction model achieves an average accuracy of 0.87, precision of 0.85 and recall of 0.88 on 18 versions of a large mobile application.

No abstract

No abstract