Towards a Prototype Based Explainable JavaScript Vulnerability Prediction Model

This is the dataset we used in our paper entitled "Towards a Prototype Based Explainable JavaScript Vulnerability Prediction Model". The manually validated dataset contains various several static source code metrics along with vulnerability fixing hashes for numerous vulnerabilities. For more details, you can read the paper here. Security has become a central and unavoidable aspect of today’s software development. Practitioners and researchers have proposed many code analysis tools and techniques to mitigate security risks. These tools apply static and dynamic analysis or, more recently, machine learning. Machine learning models can achieve impressive results in finding and forecasting possible security issues in programs. However, there are at least two areas where most of the current approaches fall short of developer demands: explainability and granularity of predictions. In this paper, we propose a novel and simple yet, promising approach to identify potentially vulnerable source code in JavaScript programs. The model improves the state-of-the-art in terms of explainability and prediction granularity as it gives results at the level of individual source code lines, which is fine-grained enough for developers to take immediate actions. Additionally, the model explains each predicted line (i.e., provides the most similar vulnerable line from the training set) using a prototype-based approach. In a study of 186 real-world and confirmed JavaScript vulnerability fixes of 91 projects, the approach could flag 60% of the known vulnerable lines on average by marking only 10% of the code-base, but in certain cases the model identified 100% of the vulnerable code lines while flagging only 8.72% of the code-base. If you wish to use our dataset, please cite this dataset, or the corresponding paper: @inproceedings{mosolygo2021towards, title={Towards a Prototype Based Explainable JavaScript Vulnerability Prediction Model}, author={Mosolyg{\'o}, Bal{\'a}zs and V{\'a}ndor, Norbert and Antal, G{\'a}bor and Heged{\H{u}}s, P{\'e}ter and Ferenc, Rudolf}, booktitle={2021 International Conference on Code Quality (ICCQ)}, pages={15--25}, year={2021}, organization={IEEE}