AI-powered vulnerability detection for secure source code development.

Rajapaksha, Sampath; Senanayake, Janaka; Kalutarage, Harsha; Al-Kadri, Mhd Omar

Abstract

Vulnerable source code in software applications is causing paramount reliability and security issues. Software security principles should be integrated to reduce these issues at the early stages of the development lifecycle. Artificial Intelligence (AI) could be applied to detect vulnerabilities in source code. In this research, a Machine Learning (ML) based method is proposed to detect source code vulnerabilities in C/C++ applications. Furthermore, Explainable AI (XAI) was applied to support developers in identifying vulnerable source code tokens and understanding their causes. The proposed model can detect whether the code is vulnerable or not in binary classification with 0.96 F1-Score. In case of vulnerability type detection, a multi-class classification based on CWE-ID, the model achieved 0.85 F1-Score. Several ML classifiers were tested, and the Random Forest (RF) and Extreme Gradient Boosting (XGB) performed well in binary and multi-class approaches respectively. Since the model is trained on a dataset containing actual source codes, the model is highly generalizable.

Citation

RAJAPAKSHA, S., SENANAYAKE, J., KALUTARAGE, H. and AL-KADRI, M.O. 2023. AI-powered vulnerability detection for secure source code development. In Bella, G., Doinea, M. and Janicke, H. (eds.) Innovative security solutions for information technology and communications: revised selected papers of the 15th International conference on Security for information technology and communications 2022 (SecITC 2022), 8-9 December 2022, [virtual conference]. Lecture notes in computer sciences, 13809. Cham: Springer [online], pages 275-288. Available from: https://doi.org/10.1007/978-3-031-32636-3_16

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2022 International conference on Security for information technology and communications (SecITC 2022)
• Start Date: Dec 8, 2022
• End Date: Dec 9, 2022
• Acceptance Date: Nov 21, 2022
• Online Publication Date: May 12, 2023
• Publication Date: Dec 31, 2023
• Deposit Date: Jul 3, 2023
• Publicly Available Date: May 13, 2024
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 275-288
• Series Title: Lecture notes in computer sciences
• Series Number: 13809
• Series ISSN: 0302-9743; 1611-3349
• Book Title: Innovative security solutions for information technology and communications: revised selected papers of the 15th International conference on Security for information technology and communications 2022 (SecITC 2022), 8-9 December 2022, [virtual conference]
• ISBN: 9783031326356; 9783031326363
• DOI: https://doi.org/10.1007/978-3-031-32636-3_16
• Keywords: Source code vulnerability; Machine learning; Software security; Vulnerability scanners
• Public URL: https://rgu-repository.worktribe.com/output/1961786