Applying Deep Learning and Vector Representation for Software Vulnerabilities Detection
| Title | Applying Deep Learning and Vector Representation for Software Vulnerabilities Detection |
| Publication Type | Conference Paper |
| Year of Publication | 2018 |
| Authors | Pechenkin, Alexander, Demidov, Roman |
| Conference Name | Proceedings of the 11th International Conference on Security of Information and Networks |
| Publisher | ACM |
| Conference Location | New York, NY, USA |
| ISBN Number | 978-1-4503-6608-3 |
| Keywords | compositionality, Deep Learning, Human Behavior, integer overflow, Metrics, Neural networks, pubcrawl, Resiliency, vector representations, vulnerability assessment, vulnerability detection |
| Abstract | This paper 1 addresses a problem of vulnerability detection in software represented as assembly code. An extended approach to the vulnerability detection problem is proposed. This work concentrates on improvement of neural network-based approach described in previous works of authors. The authors propose to include the morphology of instructions in vector representations. The bidirectional recurrent neural network is used with access to the execution traces of the program. This has significantly improved the vulnerability detecting accuracy. |
| URL | http://doi.acm.org/10.1145/3264437.3264489 |
| DOI | 10.1145/3264437.3264489 |
| Citation Key | pechenkin_applying_2018 |