计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (9): 385-394.doi: 10.11896/jsjkx.260600033

• 信息安全 • 上一篇    下一篇

基于联邦学习的三支安全决策

王书谊1, 张炜2, 徐健锋1,4, 苗夺谦3, 姚一豫4   

  1. 1 南昌大学数学与计算机学院 南昌 330000
    2 南昌大学软件学院 南昌 330000
    3 同济大学计算机科学与技术学院 上海 201804
    4 加拿大里贾那大学计算机系 里贾纳 S4S 0A2
  • 收稿日期:2026-05-03 修回日期:2026-07-06 出版日期:2026-09-15 发布日期:2026-09-10
  • 通讯作者: 徐健锋(jianfeng_x@ncu.edu.cn)
  • 作者简介:(w592969166@126.com)
  • 基金资助:
    国家自然科学基金(62266032);国家科技重大专项(2025ZD1009305);江西省自然科学基金(20252BAC250130)

Three-way Security Decision-making Based on Federated Learning

WANG Shuyi1, ZHANG Wei2, XU Jianfeng1,4, MIAO Duoqian3, YAO Yiyu4   

  1. 1 School of Mathematics and Computer Sciences,Nanchang University,Nanchang 330000,China
    2 School of Software,Nanchang University,Nanchang 330000,China
    3 School of Computer Science and Technology,Tongji University,Shanghai 201804,China
    4 Department of Computer Science,University of Regina,Regina S4S 0A2,Canada
  • Received:2026-05-03 Revised:2026-07-06 Published:2026-09-15 Online:2026-09-10
  • About author:WANG Shuyi,born in 2000,doctoral candidate.His main research interests include granular computing and uncertain artificial intelligence.
    XU Jianfeng,born in 1973,Ph.D,professor.His main research interests include artificial intelligence,smart healthcare,granular computing,and stream computing.
  • Supported by:
    National Natural Science Foundation of China(62266032),National Science and Technology Major Project of China(2025ZD1009305),and Jiangxi Provincial Natural Science Foundation(20252BAC250130).

PDF (PC)

300

摘要： 在多机构联合安全决策场景中,存在隐私保护的约束要求,联邦学习能够为此类场景提供数据不出本地的协同决策方法。但经典的基于联邦学习的决策算法往往采用传统二元决策机制,该机制对不确定问题的处理能力有限。三支决策是一种不确定问题的求解方法,其对不确定性决策对象能进行更为审慎的延迟判定。对此,基于三支决策理论,提出了一种联邦三支安全决策框架(FL-3WSD),该框架在局部规则生成、多源规则融合和目标对象监控3个层面引入三支决策机制,包括参与方侧局部三支规则生成、中央云服务器侧三支多源规则融合以及目标对象三支监控方法。在本框架中,中央云服务器首先向各参与方下发训练模型及相关参数。然后,各参与方利用数据聚类及序贯三支决策方法实现了决策规则提取,并上传至中央云服务器。最后,由中央云服务器进行决策规则汇总、模糊融合,并结合三支决策机制生成全局三支安全决策表,最终用于目标对象的联合判定。实验结果表明,与经典采用二元决策机制的联邦决策方法相比,FL-3WSD框架在决策精度和误判风险控制等方面具有明显优势,体现出较好的科学价值和应用前景。

关键词: 三支决策, 联邦学习, 隐私保护, 模糊等价类, 不确定性

Abstract: In multi-institutional joint security decision-making scenarios,federated learning provides a collaborative decision-ma-king approach that enables data to remain local under privacy-preservation constraints.However,conventional federated-learning-based decision-making algorithms often adopt a traditional binary decision mechanism,which has limited capability in handling uncertainty.Three-way decision is an effective method for addressing uncertain problems,as it enables more prudent deferred judgments for uncertain decision objects.Based on three-way decision theory,this paper proposes a federated three-way security decision-making framework,termed FL-3WSD.The proposed framework introduces the three-way decision mechanism into three levels:local rule generation,multi-source rule fusion,and target object monitoring,including local three-way rule generation on the participant side,three-way multi-source rule fusion on the central cloud server side,and three-way monitoring for target objects.In this framework,the central cloud server first distributes the training model and related parameters to each participant.Then,each participant employs data clustering and sequential three-way decision methods to extract decision rules and uploads them to the central cloud server.Finally,the central cloud server aggregates and fuzzily fuses the decision rules,and further incorporates the three-way decision mechanism to generate a global three-way security decision table,which is ultimately used for the joint judgment of target objects.Compared with classical federated decision-making methods based on binary decision mechanisms,the experimental results show that the FL-3WSD framework achieves clear advantages in decision accuracy and misclassification risk control,demonstrating promising scientific value and application prospects.

Key words: Three-way decision, Federated learning, Privacy preservation, Fuzzy equivalence class, Uncertainty

中图分类号: 

  • TP309.2
[1] LRASHID M,SHARMA M.AI-Assisted Diagnosis and Treatment Planning－A Discussion of How AI Can Assist Healthcare Professionals in Making More Accurate Diagnoses and Treatment Plans for Diseases[J].AI in Disease Detection:Advancements and Applications,2025(1):313-336.
[2] ISEAL S,JOSEPH O,JOSEPH S.AI in financial services:Using big data for risk assessment and fraud detection[J].Journal of Financial Technology,2026,12(3):45-62.
[3] ZHANG G.The research on an electronic evidence forensic system for cross-border cybercrime[J].Journal of Digital Forensics,Security and Law,2023,18(2):123-145.
[4] BÁRCENA J L C,DUCANGE P,MARCELLONI F,et al.Increasing trust in AI through privacy preservation and model explainability:Federated Learning of Fuzzy Regression Trees[J].Information Fusion,2025,113:102598.
[5] PANG M,XU H,HUANG Z,et al.Breaking data silos in Parkinson’s disease diagnosis:An adaptive federated learning approach for privacy-preserving facial expression analysis[C] //Proceedings of the AAAI Conference on Artificial Intelligence.2025:14352-14360.
[6] KAMBALA G.Data Privacy in Cloud Computing:A Comparative Study of Privacy Preserving Techniques[J].International Journal of Scientific Research and Management,2025,13(1):1299-1316.
[7] EUROPEAN PARLIAMENT,COUNCIL OF THE EUROPEAN UNION.Regulation(EU) 2016/679 of the European Parliament and of the Council[R].Official Journal of the European Union,2016,L119:1-88.
[8] MCMAHAN B,MOORE E,RAMAGE D,et al.Communica-tion-efficient learning of deep networks from decentralized data[C] //Artificial Intelligence and Statistics.PMLR,2017:1273-1282.
[9] HARIPRIYA R,KHARE N,PANDEY M.Privacy-preservingfederated learning for collaborative medical data mining in multi-institutional settings[J].Scientific Reports,2025,15(1):12482.
[10] DUSI P,AFZAL M.Federated Optimizing for Distributing Resources Across Tenants[C] //2025 International Conference on Intelligent Control,Computing and Communications(IC3).IEEE,2025:1035-1042.
[11] ZHANG X,GUO C.Research on Open Innovation IntelligentDecision-Making of Cross-Border E-Commerce Based on Fede-rated Learning[J].Mathematical Problems in Engineering,2022,2022(1):9253634.
[12] DHUMRAS H,SHUKLA P K,BAJAJ R K,et al.On federated learning-oriented q-rung picture fuzzy TOPSIS/VIKOR decision-making approach in electronic marketing strategic plans[J].IEEE Transactions on Consumer Electronics,2024,70(1):2557-2565.
[13] STERGIOU K D,PSANNIS K E,ROUMELIOTIS M,et al.Optimising decision making on communication systems:The fede-rated learning approach[C] //2021 IEEE 9th International Conference on Information,Communication and Networks(ICICN).IEEE,2021:119-123.
[14] KAYAALP M,INAN Y,KOIVUNEN V,et al.On the fusionstrategies for federated decision making[C] //2023 IEEE Statistical Signal Processing Workshop.IEEE,2023:270-274.
[15] LI C,LI F,HAO Z,et al.An IoT cross-domain access decision-making method based on federated learning[J].Wireless Communications and Mobile Computing,2021(2021):8005769.
[16] JIN Q,JIANG H Y,YU Y,et al.Multi-level personalized k-anonymity privacy-preserving model based on sequential three-way decisions[J].Expert Systems with Applications,2024,239:122343.
[17] ALI W,NAUMAN M,AZAM N.A privacy enhancing modelfor Internet of Things using three-way decisions and differential privacy[J].Computers & Electrical Engineering,2022,100:107894.
[18] XU J F,WEI Y P,CHEN Y X.A three-way trajectory privacy-preserving model based on multi-feature fusion[J].Applied Soft Computing,2024,158:111591.
[19] LLOYD S.Least squaresquantization in PCM [J].IEEE Transactions on Information Theory,1982,28(2):129-137.
[20] DU M,ZHAO J,SUN J,et al.M3w:Multistep three-way clustering[J].IEEE Transactions on Neural Networks and Learning Systems,2024,35(4):5627-5640.
[21] YAO Y,YANG J.Granular rough sets and granular shadowed sets:Three-way approximations in Pawlak approximation spaces[J].International Journal of Approximate Reasoning,2022,142:231-247.
[22] YAO Y.Three-way conflict analysis:reformulations and extensions of the Pawlak model[J].Knowledge-Based Systems,2019,180:26-37.
[23] ZHANG C,HOU H,SANGAIAH A K,et al.Efficient mobilerobot navigation based on federated learning and three-way decisions[C] //International Conference on Neural Information Processing.Singapore:Springer Nature Singapore,2023:408-422.
[24] BHANDARY R,GHOSH B K.Credit card default prediction:An empirical analysis on predictive performance using statistical and machine learning methods[J].Journal of Risk and Financial Management,2025,18(1):23.
[25] SAJID M,MALIK K R,ALMOGREN A,et al.Enhancing intrusion detection:a hybrid machine and deep learning approach[J].Journal of Cloud Computing,2024,13(1):123.
[26] DENNIS D K,LI T,SMITH V.Heterogeneity for the Win:One-Shot Federated Clustering[C] //Proceedings of the 38th International Conference on Machine Learning.PMLR,2021.
[27] ZHANG H,LI T,SMITH V.Dynamically Weighted Federated K-Means[C] //Proceedings of the International Conference on Learning Representations.2023.
[28] GARST S,REINDERS M.Federated k-means clustering[C] //International Conference on Pattern Recognition.Cham:Sprin-ger Nature Switzerland,2024:107-122.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发