Source Code Vulnerability Detection: Combining Code Language Models and Code Property Graphs

arXiv:2404.14719v1 Announce Type: new
Abstract: Currently, deep learning successfully applies to code vulnerability detection by learning from code sequences or property graphs. However, sequence-based methods often overlook essential code attributes such as syntax, control flow, and data dependencies, whereas graph-based approaches might underestimate the semantics of code and face challenges in capturing long-distance contextual information.
To address this gap, we propose Vul-LMGNN, a unified model that combines pre-trained code language models with code property graphs for code vulnerability detection. Vul-LMGNN …

arxiv attributes code code vulnerability control cs.cr data deep learning dependencies detection flow graph graphs language language models property semantics source code vulnerability vulnerability detection