VulDeBERT: A Vulnerability Detection System Using BERT

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

43 Scopus citations

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.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages69-74
Number of pages6
ISBN (Electronic)9781665476799
DOIs
StatePublished - 2022
Externally publishedYes
Event33rd IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2022 - Virtual, Online, United States
Duration: 31 Oct 20223 Nov 2022

Publication series

NameProceedings - 2022 IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2022

Conference

Conference33rd IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2022
Country/TerritoryUnited States
CityVirtual, Online
Period31/10/223/11/22

Keywords

  • Code Gadget
  • Vulnerability Detection

Fingerprint

Dive into the research topics of 'VulDeBERT: A Vulnerability Detection System Using BERT'. Together they form a unique fingerprint.

Cite this