SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities
This addresses the critical issue of software security for developers and users, offering a systematic approach to vulnerability detection, though it is incremental as it builds on deep learning methods for a specific domain.
The authors tackled the problem of detecting software vulnerabilities in C/C++ source code by proposing SySeVR, a deep learning framework that incorporates syntax and semantic information, resulting in the detection of 15 unreported vulnerabilities, including 7 unknown ones reported to vendors.
The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by the many vulnerabilities reported on a daily basis. This calls for machine learning methods for vulnerability detection. Deep learning is attractive for this purpose because it alleviates the requirement to manually define features. Despite the tremendous success of deep learning in other application domains, its applicability to vulnerability detection is not systematically understood. In order to fill this void, we propose the first systematic framework for using deep learning to detect vulnerabilities in C/C++ programs with source code. The framework, dubbed Syntax-based, Semantics-based, and Vector Representations (SySeVR), focuses on obtaining program representations that can accommodate syntax and semantic information pertinent to vulnerabilities. Our experiments with 4 software products demonstrate the usefulness of the framework: we detect 15 vulnerabilities that are not reported in the National Vulnerability Database. Among these 15 vulnerabilities, 7 are unknown and have been reported to the vendors, and the other 8 have been "silently" patched by the vendors when releasing newer versions of the pertinent software products.