• Journal of the Korea Society of Computer and Information
• /
• v.22 no.3
• /
• pp.17-25
• /
• 2017

In this paper, we compared four analyzers Clang, CppCheck, Compass, and a commercial one from a domestic startup using the NIST's Juliet test suit and STONESOUP that is introduced recently. Tools showed detection efficacy in the order of Clang, CppCheck, the domestic one, and Compass under Juliet tests; and Clang, the domestic one, Compass, and CppCheck under STONESOUP tests. We expect it would be desirable to utilize symbolic execution for vulnerability analysis in the future. On the other hand, the results of tool evaluation also testifies that Juliet and STONESOUP as a benchmark for static analysis tools can reveal differences among tools. Finally, each analyzer has different CWEs that it can detect all given test programs. This result can be used for selection of proper tools with respect to specific CWEs.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.45-52
• /
• 2020

Traditional methods of detecting security vulnerabilities in source-code require a lot of time and effort. If there is good data, the issue could be solved by using the data with machine learning. Thus, this paper proposes a source-code vulnerability detection method based on machine learning. Our method employs the code2vec model that has been used to propose the names of methods, and uses as a data set, Juliet Test Suite that is a collection of common security vulnerabilities. The evaluation shows that our method has high precision of 97.3% and recall rates of 98.6%. And the result of detecting vulnerabilities in open source project shows hopeful potential. In addition, it is expected that further progress can be made through studies covering with vulnerabilities and languages not addressed here.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.12
• /
• pp.89-94
• /
• 2018

In this paper, we implemented a static analysis tool for weakness. We implemented on JavaCC using syntax information and control flow information among various information. We also tested the performance of the tool using Juliet-test suite on Eclipse. We were classified using information necessary for diagnosis and diagnostic methods were studied and implemented. By mapping the information obtained at each compiler phase the security weakness, we expected to link the diagnostic method with the program analysis information to the security weakness. In the future, we will extend to implement diagnostic tools using other analysis information.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.801-802
• /
• 2023

시큐어 코딩은 해킹 등 사이버 공격의 원인인 보안 취약점을 제거해 안전한 소프트웨어를 개발하는 SW 개발 기법을 의미한다. 개발자의 실수나 논리적 오류로 인해 발생할 수 있는 문제점을 사전에 차단하여 대응하고자 하는 것이다. 그러나 현재 시큐어 코딩에는 오탐과 미탐의 문제가 발생한다는 단점이 있다. 따라서 본 논문에서는 오탐과 미탐이 발생하는 단점을 해결하고자 머신러닝 알고리즘을 활용하여 AI 기반으로 개발자의 실수나 논리적 오류를 탐지하는 시큐어 코딩 도구를 만들고자 한다. 다양한 모델을 사용하여 보안 취약점을 모아놓은 Juliet Test Suite를 전처리하여 학습시켰고, 정확도를 높이기 위한 과정 중에 있다. 향후 연구를 통해 정확도를 높여 정확한 시큐어 코딩 점검 도구를 개발할 수 있을 것이다.