An Intelligent Framework for Automated Software Vulnerability Detection and Secure Code Generation Using Large Language Models

Authors

  • Ravi Varman Author

Keywords:

Large language models; software vulnerability detection; secure code generation; automated program repair; static analysis; software security; code intelligence.

Abstract

Large language models (LLMs) are increasingly used to explain source code, identify defects, generate programs, and propose software repairs. Their ability to interpret natural-language requirements and broad code context creates opportunities for security-aware development; however, syntactically correct and functionally plausible code is not necessarily secure. LLMs may overlook data-flow dependencies, generate insecure constructs, misclassify vulnerabilities, or recommend patches that introduce regressions. This review examines research on LLM-assisted vulnerability detection, secure code generation, and automated vulnerability repair. It synthesizes findings from recent surveys, empirical evaluations, benchmark studies, and foundational vulnerability datasets. The literature indicates that LLMs are promising as contextual reasoning and triage components, but their reliability varies with programming language, vulnerability class, input representation, prompt design, and evaluation method. Purely generative approaches are therefore insufficient for high-assurance use. The paper proposes a conceptual hybrid framework combining code-context preparation, LLM reasoning, deterministic static and dynamic analysis, patch validation, and human approval. It also identifies research priorities in benchmark reproducibility, multi-language coverage, explainability, secure-by-construction generation, and lifecycle integration. As a structured narrative review, this article does not claim new experimental results; its contribution is a synthesis and design-oriented framework for trustworthy LLM-assisted software security

References

1. X. Zhou, S. Cao, X. Sun, and D. Lo, “Large Language Model for Vulnerability Detection and Repair: Literature Review and the Road Ahead,” ACM Transactions on Software Engineering and Methodology, vol. 34, no. 5, Art. 145, 2025. doi: 10.1145/3708522.

2. A Systematic Review on Detection, Repair, and Explanation of Vulnerabilities in Source Code Using Large Language Models,” IEEE Access, vol. 13, pp. 192263–192293, 2025. doi: 10.1109/ACCESS.2025.3631363.

3. Kasarla, S. R. (2025). A test case prioritization framework for efficient regression testing in large-scale software systems. International Journal of Applied Mathematics, 38(2s), 1648-1661.

4. A. Negri-Ribalta, A. Geraud-Stewart, and G. Lenzini, “A systematic literature review on the impact of AI models on the security of code generation,” Frontiers in Data Science, vol. 7, 2024. doi: 10.3389/fdata.2024.1386720.

5. When Software Security Meets Large Language Models: A Survey,” IEEE/CAA Journal of Automatica Sinica, available online Jan. 2025. doi: 10.1109/JAS.2024.124971.

6. L. Zhang, Q. Zou, A. Singhal, X. Sun, and P. Liu, “Evaluating Large Language Models for Real World Vulnerability Repair in C/C++ Code,” National Institute of Standards and Technology, June 19, 2024.

7. Y. Nie et al., “SECODEPLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code GenAI,” Advances in Neural Information Processing Systems 38, Datasets and Benchmarks Track, 2025. doi: 10.52202/085713-0447.

8. J. Peng, L. Cui, K. Huang, J. Yang, and B. Ray, “CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation,” in Proc. 2nd IEEE/ACM International Workshop on Large Language Models for Code (LLM4Code), 2025.

9. F. Zubair, M. Al-Hitmi, and C. Catal, “The use of large language models for program repair,” Computer Standards & Interfaces, vol. 93, Art. 103951, 2025. doi: 10.1016/j.csi.2024.103951.

10. Large Language Models for Software Engineering: A Systematic Literature Review,” ACM Transactions on Software Engineering and Methodology, vol. 33, no. 8, Art. 220, 2024. doi: 10.1145/3695988.

11. S. Kaniewski, F. Schmidt, M. Enzweiler, M. Menth, and T. Heer, “A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models,” arXiv:2507.22659, 2025. (Preprint; supplementary evidence.)

12. Kolukuri, N. R. (2025). Beyond dashboards: Designing decision-centric analytics systems that transform organizational decision-making.

13. Liu, B. (2026). State-grounded conversational agency in LLM workflow systems: A human-centered framework for trust, control, and accountable workflow orchestration. Journal of Intelligent Decision Making and Information Science, 3(13s), 411-437.

14. S. R. Kasarla, “An Empirical Analysis of Software Maintainability Using Code Quality and Complexity Metrics,” Journal of Information Systems Engineering and Management, vol. 10, no. 4, pp. 2923–2932, 2025. [Online]. Available: https://jisem-journal.com/index.php/journal/article/view/15365

Downloads

Published

20-05-2026

How to Cite

An Intelligent Framework for Automated Software Vulnerability Detection and Secure Code Generation Using Large Language Models. (2026). Innovative Journal of Computing, Security and Digital Technologies, 1(2), 21-29. https://ijcdst.in/index.php/about/article/view/20

Similar Articles

1-10 of 16

You may also start an advanced similarity search for this article.