TY - GEN
T1 - VulDeBERT
T2 - 33rd IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2022
AU - Kim, Soolin
AU - Choi, Jusop
AU - Ahmed, Muhammad Ejaz
AU - Nepal, Surya
AU - Kim, Hyoungshick
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Code Gadget
KW - Vulnerability Detection
UR - https://www.scopus.com/pages/publications/85146314148
U2 - 10.1109/ISSREW55968.2022.00042
DO - 10.1109/ISSREW55968.2022.00042
M3 - Conference contribution
AN - SCOPUS:85146314148
T3 - Proceedings - 2022 IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2022
SP - 69
EP - 74
BT - Proceedings - 2022 IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2022
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 31 October 2022 through 3 November 2022
ER -