Enhancing Software Defect Prediction Security via Federated BLSTM with Differential Privacy

Authors

  • Aunik Hasan Mridul

    Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh
  • Raihan Jamil

    Department of Data Science and Analytics, University of Hertfordshire, Hatfield AL10 9AB, UK
  • Md Injamul Haque

    Department of Artificial Intelligence Systems, EPITA – School of Engineering and Computer Science, 93300 Aubervilliers, France
  • Niazi Mahrab

    Department of Computer Science, Ravensbourne University London, London SE10 0EW, UK
  • Sartaz Islam

    Department of Computing and Mathematical Sciences, University of Greenwich, London SE10 9LS, UK
  • Mohammad Abdullah Al Nayeem Khan

    Department of Computer Science & Engineering, Jahangirnagar University, Dhaka 1342, Bangladesh
  • Nowreen Ahsan

    Department of Data Science, Clarkson University, Potsdam, NY 13699, USA
  • Md Abdur Rakib

    Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh

DOI:

https://doi.org/10.30564/jeis.v8i2.13303
Received: 16 March 2026 | Revised: 26 May 2026 | Accepted: 5 June 2026 | Published Online: 22 June 2026

Abstract

Software Defect Prediction (SDP) is an issue of paramount importance for improvement of software quality but data isolation and privacy concerns across organizations affects efficacy of SDP. By making use of a Federated Learning (FL) framework in combination with Differential Privacy (DP) for collective learning without exchanging any raw data, we provide a unique solution to this problem. The study makes use of advanced deep learning architectures the baseline Neural Network (NN), the sequential Long Short-Term Memory (LSTM) and the contextual Bidirectional LSTM (BLSTM) that were trained on the ten different, non-IID client datasets (software projects). Data processing included logarithmic transformation, Min Max Scaling, while the Synthetic Minority Over-sampling Technique (SMOTE) algorithm was used to address local class imbalance. The application of DP noise ensured the privacy of the model updates by quantifying them before aggregation using FedAvg. The results are a definite success for recurrent models with the BLSTM network coming on top, achieving a peak Global Accuracy of 99.05% and an F1-Score of 98.9% with the constraint of FL-DP. In comparison, the centralized, non-private BLSTM had slightly better performance in terms of accuracy, 99.3%, proving that the FL-DP framework is able to preserve close to optimal performance while increasing data security drastically. These results confirm that FL-DP is a powerful, safe and open-source paradigm for collaborative SDP, which enables a base solution for organizations that need to achieve high predictive power while maintaining high data confidentiality.

Keywords:

Federated Learning; Software Defect Prediction; Differential Privacy; BLSTM; Deep Learning; Class Imbalance

References

[1] Alsaeedi, A., Khan, M.Z., 2019. Software defect prediction using supervised machine learning and ensemble techniques: A comparative study. Journal of Software Engineering and Applications. 12(5), 85–100. DOI: https://doi.org/10.4236/jsea.2019.125007

[2] Galar, M., Fernandez, A., Barrenechea, E., et al., 2012. A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews). 42(4), 463–484. DOI: https://doi.org/10.1109/tsmcc.2011.2161285

[3] Tantithamthavorn, C., Hassan, A.E., Matsumoto, K., 2018. The impact of class rebalancing techniques on the performance and interpretation of defect prediction models. IEEE Transactions on Software Engineering. 46(11), 1200–1219. DOI: https://doi.org/10.1109/tse.2018.2876537

[4] Chawla, N.V., Bowyer, K.W., Hall, L.O., et al., 2002. SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research. 16, 321–357. DOI: https://doi.org/10.1613/jair.953

[5] He, H., Bai, Y., Garcia, E.A., et al., 2008. ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China, 1–6 June 2008; pp. 1322–1328.

[6] Bennin, K.E., Tahir, A., MacDonell, S.G., et al., 2021. An empirical study on the effectiveness of data resampling approaches for cross-project software defect prediction. IET Software. 16(2), 185–199. DOI: https://doi.org/10.1049/sfw2.12052

[7] Xu, Z., Li, S., Xu, J., et al., 2019. LDFR: Learning deep feature representation for software defect prediction. Journal of Systems and Software. 158, 110402. DOI: https://doi.org/10.1016/j.jss.2019.110402

[8] He, H., Garcia, E.A., 2009. Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering. 21(9), 1263–1284. DOI: https://doi.org/10.1109/tkde.2008.239

[9] Vengatesan, S.S.P., Balajiraja, N., 2024. An ensemble model for software defect prediction using machine learning algorithms. Journal of Computational Analysis and Applications. 33(6), 628–634.

[10] Shakhovska, N., Yakovyna, V., 2021. Feature selection and software defect prediction by different ensemble classifiers. In: Strauss, C., Kotsis, G., Tjoa, A.M., et al. (Eds.). Database and Expert Systems Applications (DEXA 2021). Springer: Cham, Switzerland. pp. 307–313. DOI: https://doi.org/10.1007/978-3-030-86472-9_28

[11] Balogun, A.O., Basri, S.B., Abdulkadir, S.J., et al., 2019. Software defect prediction: Analysis of class imbalance and performance stability. Journal of Engineering Science and Technology. 14(6), 3294–3308.

[12] Cai, T., Li, X., Chen, W., et al., 2024. Blockchain-based federated learning for IoT sharing: Incentive scheme with reputation mechanism. In: Chen, J., Wen, B., Chen, T. (Eds.). Blockchain and Trustworthy Systems (BlockSys 2023). Springer: Singapore. pp. 270–284. DOI: https://doi.org/10.1007/978-981-99-8101-4_19

[13] Geçer, B.G., Tarhan, A.K., 2025. Explainable AI framework for software defect prediction. Journal of Software: Evolution and Process. 37(4), e70018. DOI: https://doi.org/10.1002/smr.70018

[14] Li, C., Song, M., Luo, Y., 2024. Federated learning based on Stackelberg game in unmanned-aerial-vehicle-enabled mobile edge computing. Expert Systems with Applications. 235, 121023. DOI: https://doi.org/10.1016/j.eswa.2023.121023

[15] Zhao, Y., Zhu, Y., Yu, Q., et al., 2022. Cross-project defect prediction considering multiple data distribution simultaneously. Symmetry. 14(2), 401. DOI: https://doi.org/10.3390/sym14020401

[16] Mridul, A.H., Armin, J.F., Saleh, M.A., et al., 2025. Optimizing Rice Health: A Comparative Evaluation of Pretrained and Custom Convolutional Neural Networks for Disease Recognition. Artificial Intelligence and Applications. DOI: https://doi.org/10.47852/bonviewAIA52026109

[17] Wu, B., Seneviratne, O., 2025. Blockchain-based framework for scalable and incentivized federated learning. In Proceedings of the WWW '25: Companion Proceedings of the ACM on Web Conference 2025, Sydney, Australia, 28 April–2 May 2025; pp. 1761–1767. DOI: https://doi.org/10.1145/3701716.3717649

[18] Nair, A.K., Coleri, S., Sahoo, J., et al., 2025. Incentivized federated learning: A survey. IEEE Transactions on Emerging Topics in Computational Intelligence. 9(5), 3190–3209. DOI: https://doi.org/10.1109/TETCI.2025.3547609

[19] Xu, J., Tang, B., Cui, H., et al., 2024. An uncertainty-aware auction mechanism for federated learning. In: Tari, Z., Li, K., Wu, H. (Eds.). Algorithms and Architectures for Parallel Processing (ICA3PP 2023). Springer: Singapore. pp. 1–18. DOI: https://doi.org/10.1007/978-981-97-0811-6_1

[20] Tang, X., Yu, H., Li, X., et al., 2024. SepALM: Audio language models are error correctors for robust speech separation. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-25), Montreal, BC, Canada, 16–22 August 2025; pp. 8204–8212.

[21] Wu, L., Guo, S., Hong, Z., et al., 2023. Long-term adaptive VCG auction mechanism for sustainable federated learning with periodical client shifting. IEEE Transactions on Mobile Computing. 23(5), 6060–6073. DOI: https://doi.org/10.1109/tmc.2023.3317063

[22] Qiao, C., Li, M., Liu, Y., et al., 2025. Transitioning from federated learning to quantum federated learning in Internet of Things: A comprehensive survey. IEEE Communications Surveys & Tutorials. 27(1), 509–545. DOI: https://doi.org/10.1109/COMST.2024.3399612

[23] Li, C., Zhang, Y., Wu, J., et al., 2024. Smart contract-based decentralized data sharing and content delivery for intelligent connected vehicles in edge computing. IEEE Transactions on Intelligent Transportation Systems. 25(10), 14535–14545. DOI: https://doi.org/10.1109/TITS.2024.3388422

[24] Alsharif, M.H., Kannadasan, R., Wei, W., et al., 2024. A contemporary survey of recent advances in federated learning: Taxonomies, applications, and challenges. Internet of Things. 27, 101251. DOI: https://doi.org/10.1016/j.iot.2024.101251

[25] Guo, J., Su, L., Liu, J., et al., 2024. Auction-based client selection for online federated learning. Information Fusion. 112, 102549. DOI: https://doi.org/10.1016/j.inffus.2024.102549

[26] Liao, H., Wang, Z., Zhou, Z., et al., 2022. Blockchain and semi-distributed learning-based secure and low-latency computation offloading in space-air-ground-integrated power IoT. IEEE Journal of Selected Topics in Signal Processing. 16(3), 381–394.

[27] Huang, J., Yang, C., Zhang, S., et al., 2024. Reinforcement learning based resource management for 6G-enabled mIoT with hypergraph interference model. IEEE Transactions on Communications. 72(7), 4179–4192.

[28] Dwork, C., 2006. Differential privacy. In: Bugliesi, M., Preneel, B., Sassone, V., et al. (Eds.). Automata, Languages and Programming. Springer: Berlin/Heidelberg, Germany. pp. 1–12. DOI: https://doi.org/10.1007/11787006_1

[29] Menzies, T., Shepperd, M., 2004. jm1. Zenodo. DOI: https://doi.org/10.5281/zenodo.268514

Downloads

How to Cite

Mridul, A. H., Jamil, R., Haque, M. I., Mahrab, N., Islam, S., Khan, M. A. A. N., Ahsan, N., & Rakib, M. A. (2026). Enhancing Software Defect Prediction Security via Federated BLSTM with Differential Privacy. Journal of Electronic & Information Systems, 8(2), 1–13. https://doi.org/10.30564/jeis.v8i2.13303

Issue

Vol. 8 , Iss. 2 (October 2026)

Article Type

ARTICLE

License

Copyright © 2026 Aunik Hasan Mridul, Raihan Jamil, Md Injamul Haque, Niazi Mahrab, Sartaz Islam, Mohammad Abdullah Al Nayeem Khan, Nowreen Ahsan, Md Abdur Rakib

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC