Volltext-Downloads (blau) und Frontdoor-Views (grau)

Deep-Learning-based Vulnerability Detection in Binary Executables

  • The identification of vulnerabilities is an important element in the software development life cycle to ensure the security of software. While vulnerability identification based on the source code is a well studied field, the identification of vulnerabilities on basis of a binary executable without the corresponding source code is more challenging. Recent research has shown, how such detection canThe identification of vulnerabilities is an important element in the software development life cycle to ensure the security of software. While vulnerability identification based on the source code is a well studied field, the identification of vulnerabilities on basis of a binary executable without the corresponding source code is more challenging. Recent research has shown, how such detection can be achieved by deep learning methods. However, that particular approach is limited to the identification of only 4 types of vulnerabilities. Subsequently, we analyze to what extent we could cover the identification of a larger variety of vulnerabilities. Therefore, a supervised deep learning approach using recurrent neural networks for the application of vulnerability detection based on binary executables is used. The underlying basis is a dataset with 50,651 samples of vulnerable code in the form of a standardized LLVM Intermediate Representation. The vectorised features of a Word2Vec model are used to train different variations of three basic architectures of recurrent neural networks (GRU, LSTM, SRNN). A binary classification was established for detecting the presence of an arbitrary vulnerability, and a multi-class model was trained for the identification of the exact vulnerability, which achieved an out-of-sample accuracy of 88% and 77%, respectively. Differences in the detection of different vulnerabilities were also observed, with non-vulnerable samples being detected with a particularly high precision of over 98%. Thus, the methodology presented allows an accurate detection of 23 (compared to 4) vulnerabilities.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Document Type:Article (unreviewed)
Title (English):Deep-Learning-based Vulnerability Detection in Binary Executables
Author:Andreas SchaadGND, Dominik BinderGND
Year of Publication:2022
Date of first Publication:2022/11/25
First Page:1
Last Page:21
DOI:https://doi.org/10.48550/arXiv.2212.01254
URL:https://www.researchgate.net/publication/366004738
Language:English
Institutes:Fakultät Medien (M) (ab 22.04.2021)
Institutes:Bibliografie
Tag:Cryptography
Open Access: Open Access 
 Diamond 
Relevance:Wiss. Zeitschriftenartikel unreviewed
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International
Comment:
Preprint
ArXiv Id:http://arxiv.org/abs/2212.01254
ArXiv Id:http://arxiv.org/abs/2212.01254v1