DeeDP: vulnerability detection and patching based on deep learning
dc.contributor.author | Savchenko, A. | |
dc.contributor.author | Fokin, O. | |
dc.contributor.author | Chernousov, A. | |
dc.contributor.author | Sinelnikova, O. | |
dc.contributor.author | Osadchyi, S. | |
dc.date.accessioned | 2020-10-15T15:02:50Z | |
dc.date.available | 2020-10-15T15:02:50Z | |
dc.date.issued | 2020 | |
dc.description.abstracten | We present the DeeDP system for automatic vulnerabilities detection and patch providing. DeeDP allows to detect vulnerabilities in C/C++ source code and generate patch for fixing detected issue. This system uses deep learning methods to organize rules for deciding whether a code fragment is vulnerable. Patch generation processes can be performed based on neural network and rule-based approaches. The system uses the abstract syntax tree (AST) representations of the source code fragments. We have tested effectiveness of our approach on different open source projects. For example, Microsoft/Terminal (https://github.com/microsoft/Terminal) was analyzed with DeeDP: our system detected security issue and generated patch which was successfully approved and applied by Microsoft maintainers. | uk |
dc.format.pagerange | Pp. 56-62 | uk |
dc.identifier.citation | DeeDP: vulnerability detection and patching based on deep learning / A. Savchenko, O. Fokin, A. Chernousov, O. Sinelnikova, S. Osadchyi // Theoretical and Applied Cybersecurity : scientific journal. – 2020. – Vol. 2, Iss. 1. – Pp. 56–62. – Bibliogr.: 21 ref. | uk |
dc.identifier.doi | https://doi.org/10.20535/tacs.2664-29132020.1.209465 | |
dc.identifier.uri | https://ela.kpi.ua/handle/123456789/36794 | |
dc.language.iso | en | uk |
dc.publisher | Igor Sikorsky Kyiv Polytechnic Institute | uk |
dc.publisher.place | Kyiv | uk |
dc.source | Theoretical and Applied Cybersecurity : scientific journal, 2020, Vol. 2, No. 1 | uk |
dc.subject | vulnerability detection | uk |
dc.subject | patch generation | uk |
dc.subject | deep learning | uk |
dc.subject.udc | 004 | uk |
dc.title | DeeDP: vulnerability detection and patching based on deep learning | uk |
dc.type | Article | uk |
Файли
Контейнер файлів
1 - 1 з 1
Вантажиться...
- Назва:
- TACS_2-1_2020_09.pdf
- Розмір:
- 770.29 KB
- Формат:
- Adobe Portable Document Format
- Опис:
Ліцензійна угода
1 - 1 з 1
Ескіз недоступний
- Назва:
- license.txt
- Розмір:
- 9.06 KB
- Формат:
- Item-specific license agreed upon to submission
- Опис: