Integrating AI models for code analysis and enhancing interpretability with explainable AI for human-readable bug detection
*B. K. KavyaCorresponding authorkavyabkphd@gmail.comDepartment of Computer Science and EngineeringJAIN (Deemed-to-be University)Bangalore, Karnataka, 562112, IndiaView full profile → , S. Annamalaiannamalaiphd@gmail.comDepartment of Computer Science and EngineeringJAIN (Deemed-to-be University)Bangalore, Karnataka, 562112, IndiaView full profile → , A. Suresh Kumarsuresha0279@gmail.comDepartment of Computer Science and EngineeringJAIN (Deemed-to-be University)Bangalore, Karnataka, 562112, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Jan 2026
- Published Online:
- 31 Aug 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2320
- Pages:
- 3017–3031
Abstract
The proposed study aims to integrate and assess the currently available AI models to provide a facility in terms of code analysis and bug detection in software development projects. Although AI has already proven to be useful in automating the bug-detection process, the interpretability of most AI-based solutions remains low, which restricts their susceptibility to developers. To resolve this challenge, the research will improve such AI models with the use of the Explainable AI (XAI) solutions, which will explain the reasons behind bugs identified to be detected in a human readable manner. The intent of this improvement is to unlock the effect of the transparency, trust, and effectiveness of the bug identification systems. The evaluation of the process of integration is carried out with real-life codebases by comparing the output of the AI models to the outcomes obtained after applying the XAI techniques. Findings show that besides the improved accuracy in detecting bugs the improved models also provide actionable and understandable information and hence the bug faults are resolved more quickly and efficiently in the development environment.
Keywords
Subject Classifications
References
[1] K. Gaddamwar, Y. Srivastava, J. Parashar, R. A. Parmar, A. K. Pandey, and V. S. Kushwah, “Deep learning for contextual bug detection and automated fixes in software systems,” in Proc. 2024 2nd Int. Conf. Advances Comput., Commun. Inf. Technol. (ICAICCIT), Faridabad, India, pp. 624–629 (2024).
[2] S. Mishra, U. Tiwari, and C. R. Kavitha, “Leveraging sequential deep learning models for robust compiler bug detection in software logs,” in Proc. 2025 3rd Int. Conf. Intell. Data Commun. Technol. Internet Things (IDCIoT), Bengaluru, India, pp. 1179–1185 (2025).
[3] J. Tripathy, S. S. Rao, S. Ashwani, and C. R. Kavitha, “Enhanced bug detection in compiler logs using stacking and explainable AI techniques,” in Proc. 2024 5th IEEE Global Conf. Advancement Technol. (GCAT), Bengaluru, India, pp. 1–6 (2024).
[4] P. Wang and Z. Guan, “Unveiling software vulnerabilities: A groundbreaking approach to defect detection utilizing CC2Vec,” in Proc. 2024 Int. Conf. Comput., Inf. Process. Advanced Educ. (CIPAE), Ottawa, ON, Canada, pp. 99–103 (2024).
[5] V. Kumar, P. Pranav, and M. Srinivas, “Smart contract cloning identification using BERT model based representation learning,” in Proc. 2023 IEEE 20th India Council Int. Conf. (INDICON), Hyderabad, India, pp. 1254–1258 (2023).
[6] X. Pan, J. Li, Z. Zhou, G. Li, X. Chen, J. Ma, J. Wu, and Q. Zhang, “Large language model-enhanced probabilistic modeling for effective static analysis alarms,” Front. Inf. Technol. Electron. Eng., vol. 26, no. 10, pp. 1926–1941 (2025), doi: 10.1631/FITEE.2500038.
[7] J. Chaudhuri, D. Thapar, A. Chaudhuri, F. Firouzi, and K. Chakrabarty, “SPICED+: Syntactical bug pattern identification and correction of Trojans in A/MS circuits using LLM-enhanced detection,” IEEE Trans. Very Large Scale Integr. (VLSI) Syst., vol. 33, no. 4, pp. 1118–1131 (2025), doi: 10.1109/TVLSI.2025.3527382.
[8] A. Gupta, M. Sharma, and A. Srivastava, “A novel dimensionality reduction-based software bug prediction using a bat-inspired algorithm,” in Proc. 2023 13th Int. Conf. Cloud Comput., Data Sci. Eng. (Confluence), Noida, India, pp. 278–285 (2023), doi: 10.1109/Confluence56041.2023.10048829.
[9] L. Ruggahakotuwa, L. Rupasinghe, and P. K. W. Abeygunawardhana, “Code vulnerability identification and code improvement using advanced machine learning,” in Proc. 2019 Int. Conf. Advancements Comput. (ICAC), Malabe, Sri Lanka, pp. 186–191 (2019), doi: 10.1109/ICAC49085.2019.9103400.
[10] J. Lu, F. Li, C. Liu, L. Li, X. Feng, and J. Xue, “CloudRaid: Detecting distributed concurrency bugs via log mining and enhancement,” IEEE Trans. Softw. Eng., vol. 48, no. 2, pp. 662–677 (2022), doi: 10.1109/TSE.2020.2999364.
[11] V. Rastogi, A. Pandey, and S. S. Yadav, “Code analysis to prioritize and fix bugs using Top-K pruning approach with help of machine learning,” in Proc. 2023 5th Int. Conf. Adv. Comput., Commun. Control Networking (ICAC3N), Greater Noida, India, pp. 1476–1482 (2023), doi: 10.1109/ICAC3N60023.2023.10541610.
[12] V. Dankan Gowda, S. V. Chakrasali, P. S. V. V. S. R. Kumar, S. A. Dhole, J. K. Patil, and S. Singh, “A novel cryptographic approach to evaluate the security of federated learning frameworks,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 5-A, pp. 1527–1536 (2025), doi: 10.47974/JDMSC-2151.
[13] K. Aldi, R. Septianto, R. Yulianto, and R. Taskia, “Multi-tool static code analysis for code smell and bug detection: A case study on the Java-Design-Patterns repository,” in Proc. 2025 Int. Conf. Inf. Technol. Res. Innov. (ICITRI), Jakarta, Indonesia, pp. 1–6 (2025), doi: 10.1109/ICITRI67507.2025.11232802.
[14] V. Dankan Gowda, D. Palanikkumar, S. Suneel, S. Dekka, T. Thiruvenkadam, and K. D. V. Prasad, “Cryptographic image-based data security strategies in wireless sensor networks,” J. Discrete Math. Sci. Cryptogr., vol. 27, no. 2-A, pp. 293–304 (2024), doi: 10.47974/JDMSC-1883.
[15] H. Sajnani, V. Saini, and C. V. Lopes, “A comparative study of bug patterns in Java cloned and non-cloned code,” in Proc. 2014 IEEE 14th Int. Working Conf. Source Code Anal. Manip. (SCAM), Victoria, BC, Canada, pp. 21–30 (2014), doi: 10.1109/SCAM.2014.12.
[16] S. V. Chakrasali, K. D. V. Prasad, P. Sarma, and M. Rahman, “Mathematical analysis of wavelet-based multi-image compression in medical diagnostics,” J. Discrete Math. Sci. Cryptogr., vol. 27, no. 2-B, pp. 675–687 (2024), doi: 10.47974/JDMSC-1912.
[17] X. Song, Y. Wu, J. Cao, B. Chen, Y. Lin, Z. Lu, D. Wang, and X. Peng, “BugMiner: Automating precise bug dataset construction by code evolution history mining,” in Proc. 38th IEEE/ACM Int. Conf. Automated Softw. Eng. (ASE), Luxembourg, Luxembourg, pp. 1919–1929 (2023), doi: 10.1109/ASE56229.2023.00201.
[18] S. T. Cynthia, “Identification and optimization of redundant code using large language models,” in Proc. 2025 IEEE/ACM 4th Int. Conf. AI Eng.—Softw. Eng. for AI (CAIN), Ottawa, ON, Canada, pp. 261–263 (2025), doi: 10.1109/CAIN62899.2025.00042.
