Using Multiple Code Representations to Prioritize Static Analysis Warnings

TL;DR

This paper presents VulRG, a deep learning-based approach that effectively ranks static analysis warnings by their likelihood of being true positives, significantly reducing developer effort in vulnerability detection.

Contribution

VulRG combines CNN and BiGRU models to predict and prioritize static analysis warnings, improving accuracy over existing methods.

Findings

Recall at Top-50% is 90.9%

VulRG improves Precision and Recall by +30% at Top-5%

Effective on a dataset of 6,620 warnings

Abstract

In order to ensure the quality of software and prevent attacks from hackers on critical systems, static analysis tools are frequently utilized to detect vulnerabilities in the early development phase. However, these tools often report a large number of warnings with a high false-positive rate, which causes many difficulties for developers. In this paper, we introduce VulRG, a novel approach to address this problem. Specifically, VulRG predicts and ranks the warnings based on their likelihoods to be true positive. To predict that likelihood, VulRG combines two deep learning models CNN and BiGRU to capture the context of each warning in terms of program syntax, control flow, and program dependence. Our experimental results on a real-world dataset of 6,620 warnings show that VulRG's Recall at Top-50% is 90.9%. This means that using VulRG, 90% of the vulnerabilities can be found by examining only 50% of the warnings. Moreover, at Top-5%, VulRG can improve the state-of-the-art approach by +30% in both Precision and Recall.