Online appendix for the RAISE'19 paper.
Authors:
Rudolf Ferenc, Péter Hegedűs, Péter Gyimesi, Gábor Antal, Dénes Bán and Tibor Gyimóthy.
Abstract:
The rapid rise of cyber-crime activities and growing number of devices threatened by them places software security issues in spotlight. As around 90% of all attacks exploit known types of security issues, finding vulnerable components and applying existing mitigation techniques is a viable practical approach for fighting against cyber-crime. In this paper, we investigate how the state-of-the-art machine learning techniques, including a popular deep learning algorithm perform in predicting functions with possible security vulnerabilities in JavaScript programs. We applied 8 machine learning algorithms to build prediction models using a new dataset constructed for this research from the vulnerability information in public databases of the Node Security Project and the Snyk platform, and code fixing patches from GitHub. We used static source code metrics as predictors and an extensive grid-search algorithm to find the best performing models. We also examined the effect of various re-sampling strategies to handle the imbalanced nature of the dataset. The best performing algorithm was KNN, which created a model for the prediction of vulnerable functions with an F-measure of 0.76 (0.91 precision and 0.66 recall). Moreover, deep learning, tree and forest based classifiers, and SVM were competitive with F-measures over 0.70. Although F-measures did not vary significantly with the re-sampling strategies, the distribution of precision and recall did change. No re-sampling seemed to produce models preferring high precision, while re-sampling strategies balanced the IR measures.
Keywords:
vulnerability, JavaScript, machine learning, deep learning, code metrics, dataset
Online appendix:
Download link for the JSVulnerabilityDataSet 1.0 (~660 KB).