Litcius/Paper detail

VulDeBERT: A Vulnerability Detection System Using BERT

Soolin Kim, Jusop Choi, Muhammad Ejaz Ahmed, ‪Surya Nepal‬, Hyoungshick Kim

202244 citationsDOI

Abstract

Deep learning technologies recently received much attention to detect vulnerable code patterns accurately. This paper proposes a new deep learning-based vulnerability detection tool dubbed VulDeBERT by fine-tuning a pre-trained language model, Bidirectional Encoder Representations from Transformers (BERT), on the vulnerable code dataset. To support VulDeBERT, we develop a new code analysis tool to extract well-represented abstract code fragments from C and C++ source code. The experimental results show that VulDeBERT outperforms the state-of-the-art tool, VulDeePecker [1] for two security vul- nerability types (CWE-119 and CWE-399). For the CWE-119 dataset, VulDeBERT achieved an Fl score of 94.6 %, which is significantly better than VulDeePecker, achieving an Fl score of 86.6 % in the same settings. Again, for the CWE-399 dataset, VulDeBERT achieved an Fl score of 97.9 %, which is also better than VulDeePecker, achieving an Fl score of 95 % in the same settings.

Topics & Concepts

Computer scienceEncoderSource codeCode (set theory)Artificial intelligenceDeep learningVulnerability (computing)Machine learningF1 scoreProgramming languageOperating systemComputer securitySet (abstract data type)Software Engineering ResearchAdvanced Malware Detection TechniquesWeb Application Security Vulnerabilities
VulDeBERT: A Vulnerability Detection System Using BERT | Litcius