Visible to the public Vulnerability Detection for Source Code Using Contextual LSTM

TitleVulnerability Detection for Source Code Using Contextual LSTM
Publication TypeConference Paper
Year of Publication2018
AuthorsXu, A., Dai, T., Chen, H., Ming, Z., Li, W.
Conference Name2018 5th International Conference on Systems and Informatics (ICSAI)
ISBN Number978-1-7281-0120-0
KeywordsCLSTM, component, compositionality, Conferences, Human Behavior, Informatics, Metrics, Neural Network, pubcrawl, Resiliency, vulnerability detection

With the development of Internet technology, software vulnerabilities have become a major threat to current computer security. In this work, we propose the vulnerability detection for source code using Contextual LSTM. Compared with CNN and LSTM, we evaluated the CLSTM on 23185 programs, which are collected from SARD. We extracted the features through the program slicing. Based on the features, we used the natural language processing to analysis programs with source code. The experimental results demonstrate that CLSTM has the best performance for vulnerability detection, reaching the accuracy of 96.711% and the F1 score of 0.96984.

Citation Keyxu_vulnerability_2018