Open Access Open Access  Restricted Access Subscription Access

CODE SENTINEL

Evangeline Aishwarya S, Srimathi D, Sriram G, Vikas B

Abstract


Software development is becoming increasingly complex, making early detection of bugs, security vulnerabilities, and code-quality issues essential for reliable applications. Code Sentinel is an AI-powered platform designed to analyse source code and identify potential software defects and security risks. The system detects issues and classifies them based on their severity and location. It provides AI-based explanations to help developers understand the causes of detected problems and suggests suitable improvements. The platform also generates a structured report containing the identified issues and recommendations. Code Sentinel can be integrated with CI/CD pipelines to automatically analyse code before deployment. The proposed system aims to reduce manual code-review effort and promote secure, reliable, and maintainable software development.

 


Full Text:

PDF

References


OWASP Foundation, OWASP Top 10:2025 – The Ten Most Critical Web Application Security Risks, OWASP Foundation, 2025. OWASP Top 10

OWASP Foundation, Source Code Analysis Tools, OWASP Foundation. OWASP Community

National Institute of Standards and Technology (NIST), Source Code Security Analysis, NIST, U.S. Department of Commerce. NIST

Z. Feng, D. Guo, D. Tang, N. Duan, X. Feng, M. Gong, L. Shou, B. Qin, T. Liu, D. Jiang, and M. Zhou, “CodeBERT: A Pre-Trained Model for Programming and Natural Languages,” Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1536–1547, 2020, doi: 10.18653/v1/2020.findings-emnlp.139. ACL Anthology

Z. Zou, T. Jiang, Y. Wang, T. Xue, N. Zhang, and J. Luan, “Code Vulnerability Detection Based on Augmented Program Dependency Graph and Optimized CodeBERT,” Scientific Reports, vol. 15, Article 39301, 2025, doi: 10.1038/s41598-025-23029-4. DOI

“Integration of Large Language Models (LLMs) and Static Analysis for Improving the Efficacy of Security Vulnerability Detection in Source Code,” Computers, Materials & Continua, vol. 86, no. 3, 2026, doi: 10.32604/cmc.2025.074566. ScienceDirect

R. Ramires, S. Bashir, M. A. Khan, M. Saadatmand, and I. Medeiros, “Friends or Foes? Combining Static Analysis Tools and LLMs for Vulnerability Detection,” 2026 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), pp. 163–172, 2026, doi: 10.1109/ICSTW72326.2026.00040. IEEE Xplore

Mhatre, N. Nader, P. Diehl, and D. Gupta, “Can LLMs Find Bugs in Code? An Evaluation from Beginner Errors to Security Vulnerabilities in Python and C++,” IEEE SoutheastCon 2026, 2026, doi: 10.1109/SoutheastCon63549.2026.11476483. IEEE Xplore

“Fine-Tuning a Vulnerability-Specific Large Language Model for a Hybrid Software Vulnerability Detection Method,” Engineering Applications of Artificial Intelligence, vol. 165, Article 113410, 2026, doi: 10.1016/j.engappai.2025.113410. ScienceDirect

S.-S. Chen, Y.-S. Hsu, T.-C. Lin, C.-K. Chen, and C.-Y. Sun, “Enhancing Static Vulnerability Alert Validation Using Large Language Models,” Journal of Systems and Software, vol. 243, Article 113040, 2026, doi: 10.1016/j.jss.2026.113040. ScienceDirect


Refbacks

  • There are currently no refbacks.