| 本文已被：浏览 1279次 下载 887次 |
码上扫一扫！ |
|
|
| 基于个性化联邦学习的跨项目软件缺陷预测方法 |
|
刘子扬1, 祝义1,2, 周湘1, 李建豪1, 袁春鸿3, 郝国生1
|
|
1.江苏师范大学 计算机科学与技术学院, 江苏 徐州 221116;2.高安全系统的软件开发与验证技术工业和信息化部重点实验室(南京航空航天大学), 江苏 南京 211106;3.Faculty of Control Systems and Robotics, Saint Petersburg National Research University of Information Technologies, Mechanics and Optics, St. Petersburg 197101, Russia
|
|
| 摘要: |
| 针对跨项目软件缺陷预测中数据隐私与项目异构性的双重挑战, 提出一个名为PRIDE-SDP的框架. 该框架的核心贡献在于深度融合了3种关键技术: 采用个性化联邦学习范式为每个异构项目定制专属预测模型, 集成提供严格数学保障的 (ε, δ)-差分隐私机制保护数据不出本地, 并设计了一个专用的时间-上下文融合网络 (temporal-contextual fusion network, TCFN)以高效地捕捉软件度量特征. 在覆盖27个开源项目和3个企业项目的6个数据集组上的实验结果验证了该框架的有效性: 与先进的跨项目缺陷预测基线相比, PRIDE-SDP平均AUC提升10.7%, F1-score提升7.3%; 在企业数据集上表现更加突出, 相较于所有先进的基线方法, MCC平均提升45.2%, Effort@20%平均提升29.5%, F1-score平均提升35.4%. 同时, 框架在提供较强隐私保障时, 其平均性能保持率仍能达到最佳性能的98%以上, 并且在成员推理攻击实验中能将攻击者的攻击准确率平均降低超过36%. 实验结果表明, PRIDE-SDP在保持高性能的同时, 有效兼顾了隐私保护与个性化适应能力. |
| 关键词: 软件缺陷预测 个性化联邦学习 差分隐私 跨项目缺陷预测 |
| DOI：10.13328/j.cnki.jos.007582 |
| 分类号:TP311 |
| 基金项目:国家自然科学基金 (62077029, 62277030); 江苏省教育科学规划 (B-b/2024/01/47); 南京航空航天大学基本科研业务费科研基地创新基金 (NJ2020022); 江苏师范大学研究生科研创新项目 (2025XKT1437) |
|
| Cross-project Software Defect Prediction Method Based on Personalized Federated Learning |
|
LIU Zi-Yang1, ZHU Yi1,2, ZHOU Xiang1, LI Jian-Hao1, YUAN Chun-Hong3, HAO Guo-Sheng1
|
|
1.School of Computer Science and Engineering, Jiangsu Normal University, Xuzhou 221116, China;2.Key Laboratory of Safety-critical Software (Nanjing University of Aeronautics and Astronautics), Ministry of Industry and Information Technology, Nanjing 211106, China;3.Faculty of Control Systems and Robotics, Saint Petersburg National Research University of Information Technologies, Mechanics and Optics, St. Petersburg 197101, Russia
|
| Abstract: |
| To address the dual challenges of data privacy and project heterogeneity in cross-project software defect prediction, this study proposes a framework named PRIDE-SDP. The core contribution of the proposed framework lies in the deep integration of three key techniques. First, a personalized federated learning paradigm is adopted to customize dedicated prediction models for heterogeneous projects. Second, an (ε, δ)-differential privacy mechanism with rigorous mathematical guarantees is integrated to ensure that data remains local. Third, a dedicated temporal-contextual fusion network (TCFN) is designed to efficiently capture software metric features. Experiments conducted on six dataset groups covering 27 open-source projects and 3 enterprise projects validate the effectiveness of the proposed framework. Compared with state-of-the-art cross-project defect prediction baselines, PRIDE-SDP achieves an average improvement of 10.7% in AUC and 7.3% in F1-score. More pronounced performance gains are observed on enterprise datasets, where average improvements of 45.2% in MCC, 29.5% in Effort@20%, and 35.4% in F1-score are obtained over all advanced baseline methods. Meanwhile, under strong privacy guarantees, the framework’s average performance retention rate remains above 98% of the optimal performance, and the attack accuracy in membership inference attack experiments is reduced by more than 36% on average. Experimental results demonstrate that PRIDE-SDP effectively balances high predictive performance with privacy protection and personalized adaptation capabilities. |
| Key words: software defect prediction (SDP) personalized federated learning differential privacy cross-project defect prediction |
