智能体互联网中隐私增强互操作框架设计与优化

居彬; 王方圆; 罗童; 张羽

doi:10.11959/j.issn.1000-0801.DXKX260297

您当前的位置：

首页 >

文章列表页 >

智能体互联网中隐私增强互操作框架设计与优化

更新时间：2026-07-21

- 智能体互联网中隐私增强互操作框架设计与优化
- Telecommunications Science (2026)
- 作者机构：
  
  1.江苏省公用信息有限公司，江苏南京 210003
  2.南京理工大学，江苏南京 210094
  3.恒安嘉新（北京）科技股份公司，北京 100086
- 作者简介：
- 基金信息：
  
  Jiangsu Provincial Frontier Technology R&D Program(BF2025004)
- DOI：10.11959/j.issn.1000-0801.DXKX260297
  CLC： TP393.08;TN915
- Received：11 May 2026，
  
  Revised：2026-07-20，
- 稿件说明：
移动端阅览
居彬, 王方圆, 罗童, et al. 智能体互联网中隐私增强互操作框架设计与优化[J/OL]. Telecommunications Science, 2026.
DOI：

居彬, 王方圆, 罗童, et al. 智能体互联网中隐私增强互操作框架设计与优化[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260297.

摘要

随着物联网与人工智能技术的深度融合，由海量智能体协同互联构成的智能体互联网（Internet of Agents）正逐步迈向深度协同。然而，智能体在互操作过程中需频繁交换状态信息与决策知识，面临严峻的隐私泄露风险。现有研究大多将隐私保护视为性能优化的附属目标，缺乏系统性的内生安全机制。为此，本文提出一种隐私增强的互操作框架。该框架首先通过数字孪生技术为每个物理智能体构建虚拟映射，在孪生空间中形成隔离的交互沙盘；进而设计基于本地差分隐私的条件生成式对抗网络（LDP-CGAN），将加噪后的本地观测在孪生空间中复原为富含语义的虚拟数据，从源头切断原始数据流；最后提出联邦多智能体深度确定性策略梯度算法（FC-MADDPG），利用虚拟数据进行协同策略训练，并引入互操作性得分指导联邦聚合，实现通信、计算与隐私资源的联合优化。在MedMNIST医疗推理任务场景中的实验表明，与传统多智能体强化学习算法相比，本框架在引入强隐私保护的同时，任务平均时延与能耗仅分别增加5.1%与6.8%；模型逆向攻击的隐私泄露率从84.5%降至13.2%。实验结果验证了本框架在保障隐私安全的同时能够有效维持系统协同效能。

Abstract

关键词

Keywords

references

Chen W , Lin X , Lee J , et al . 5G-advanced toward 6G: Past, present, and future [J ] . IEEE Journal on Selected Areas in Communications , 2023 , 41 ( 6 ): 1592 - 1619 .

Deng X , Yin J , Guan P , et al . Intelligent delay-aware partial computing task offloading for multiuser industrial internet of things through edge computing [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 4 ): 2954 - 2966 .

Feriani A , Hossain E . Single and multi-agent deep reinforcement learning for AI-enabled wireless networks: A tutorial [J ] . IEEE Communications Surveys & Tutorials , 2021 , 23 ( 2 ): 1226 - 1252 .

Li C , Gan Y , Zhang Y , et al . A cooperative computation offloading strategy with on-demand deployment of multi-UAVs in UAV-aided mobile edge computing [J ] . IEEE Transactions on Network and Service Management , 2024 , 21 ( 2 ): 2095 - 2110 .

Liu F , Chen J , Zhang Q , et al . Online MEC offloading for V2V networks [J ] . IEEE Transactions on Mobile Computing , 2023 , 22 ( 10 ): 6097 - 6109 .

Liu F , Yu H , Huang J , et al . Joint service migration and resource allocation in edge IoT system based on deep reinforcement learning [J ] . IEEE Internet of Things Journal , 2023 , 11 ( 7 ): 11341 - 11352 .

Liu W , Li B , Xie W , et al . Energy efficient computation offloading in aerial edge networks with multi-agent cooperation [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 9 ): 5725 - 5739 .

Suzuki A , Kobayashi M , Oki E . Multi-agent deep reinforcement learning for cooperative computing offloading and route optimization in multi cloud-edge networks [J ] . IEEE Transactions on Network and Service Management , 2023 , 20 ( 4 ): 4416 - 4434 .

Tang F , Chen X , Rodrigues T K , et al . Survey on digital twin edge networks (DITEN) toward 6G [J ] . IEEE Open Journal of the Communications Society , 2022 , 3 : 1360 - 1381 .

Wang M , Zhang L , Gao P , et al . Stackelberg game-based intelligent offloading incentive mechanism for a multi-UAV-assisted mobile edge computing system [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 17 ): 15679 - 15689 .

Zhang Z , Wang N , Wu H , et al . MR-DRO: A fast and efficient task offloading algorithm in heterogeneous edge/cloud computing environments [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 4 ): 3165 - 3178 .

朱威 , 马田丰 , 金友兴 , 等 . 智能体互联网潜在关键技术展望 [J ] . 信息通信技术 , 2025 , 19 ( 5 ): 48 - 54 .

Hou W , Wen H , Song H , et al . Multiagent deep reinforcement learning for task offloading and resource allocation in cybertwin-based networks [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 22 ): 16256 - 16268 .

Liu T , Tang L , Wang W , et al . Digital-twin-assisted task offloading based on edge collaboration in the digital twin edge network [J ] . IEEE Internet of Things Journal , 2021 , 9 ( 2 ): 1427 - 1444 .

Yao Z , Xia S , Li Y , et al . Cooperative task offloading and service caching for digital twin edge networks: A graph attention multi-agent reinforcement learning approach [J ] . IEEE Journal on Selected Areas in Communications , 2023 , 41 ( 11 ): 3401 - 3413 .

Yuan X , Chen J , Zhang N , et al . Digital twin-driven vehicular task offloading and IRS configuration in the Internet of vehicles [J ] . IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 12 ): 24290 - 24304 .

Yuan X M , Tian H S , Huang K D , et al . A GAN-enhanced multi-agent deep reinforcement learning for digital twin-driven edge inference and heterogeneous resource co-optimization [J ] . Chinese Journal of Computers , 2025 , 48 ( 8 ): 1763 - 1780 .

Zhang Y , Hu J , Min G . Digital twin-driven intelligent task offloading for collaborative mobile edge computing [J ] . IEEE Journal on Selected Areas in Communications , 2023 , 41 ( 10 ): 3034 - 3045 .

Zhao L , Zhao Z , Zhang E , et al . A digital twin-assisted intelligent partial offloading approach for vehicular edge computing [J ] . IEEE Journal on Selected Areas in Communications , 2023 , 41 ( 11 ): 3386 - 3400 .

Butt J S . The general data protection regulation of 2016 (GDPR) meets its sibling the artificial intelligence act of 2024: A power couple, or a clash of titans? [J ] . Acta Universitatis Danubius: Juridica , 2024 , 20 ( 2 ): 7 - 25 .

He Y , Yang M , He Z , et al . Computation offloading and resource allocation based on DT-MEC-assisted federated learning framework [J ] . IEEE Transactions on Cognitive Communications and Networking , 2023 , 9 ( 6 ): 1707 - 1720 .

Seid A M , Erbad A , Abishu H N , et al . Multi-agent federated reinforcement learning for resource allocation in UAV-enabled internet of medical things networks [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 22 ): 19695 - 19711 .

Wang Z , Hu Q , Xiong Z , et al . Resource optimization for blockchain-based federated learning in mobile edge computing [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 9 ): 15166 - 15178 .

Wu C , Li L , Zhang L , et al . Efficient GAN-based federated optimization for vehicular task offloading with mobile edge computing in 6G network [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 3 ): 2736 - 2748 .

Yang H , Zhao J , Xiong Z , et al . Privacy-preserving federated learning for UAV-enabled networks: learning-based joint scheduling and resource management [J ] . IEEE Journal on Selected Areas in Communications , 2021 , 39 ( 10 ): 3144 - 3159 .

Yin H , Wang S , Zhang K , et al . Research on asynchronous robust federated learning method in vehicle computing power network [J ] . Chinese Journal on Internet of Things , 2024 , 8 ( 4 ): 14 - 22 .

Yuan X , Chen J , Zhang N , et al . A federated bidirectional connection broad learning scheme for secure data sharing in Internet of vehicles [J ] . China Communications , 2021 , 18 ( 7 ): 117 - 133 .

Zhang R , Pan C , Wang Y , et al . Federated deep reinforcement learning for multimedia task offloading and resource allocation in MEC networks [J ] . IEICE Transactions on Communications , 2024 , E107-B( 6 ): 446 - 457 .

Zhang R , Xie Z , Yu D , et al . Digital twin-assisted federated learning service provisioning over mobile edge networks [J ] . IEEE Transactions on Computers , 2023 , 73 ( 2 ): 586 - 598 .

Zhao Y , Chen J . A survey on differential privacy for unstructured data content [J ] . ACM Computing Surveys (CSUR) , 2022 , 54 ( 10 s): 1 - 28 .

卢利颖 . AI智能体用户隐私风险与监管治理研究 [J ] . 通信世界 , 2026 ( 6 ): 39 - 40 .

武林娜 , 王淞鹤 , 吴怡 , 等 . 智能体个人信息保护风险及应对路径 [J ] . 中国信息安全 , 2026 ( 4 ): 60 - 64 .

王瑞锦 , 赖金山 , 王金波 . 边缘计算下的联邦学习：安全与隐私挑战 [J ] . 计算 , 2026 , 2 ( 4 ): 24 - 31 .

刘晓迁 , 袁明 , 钱汉伟 , 等 . 检索增强生成中的隐私保护技术综述 [J ] . 计算机应用研究 , 2026 , 43 ( 4 ): 985 - 994 .

Lowe R , Wu Y I , Tamar A , et al . Multi-agent actor-critic for mixed cooperative-competitive environments [J ] . Advances in Neural Information Processing Systems , 2017 , 30 .

Abadi M , Chu A , Goodfellow I , et al . Deep learning with differential privacy [C ] // Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security . Vienna, Austria , 2016 : 308 - 318 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

通信工程数字化监理模式的实践与探索

Establishing an intelligent agent system for network operations and maintenance

SRv6 dynamic performance optimization method based on machine learning

Heterogeneous computing power scheduling system and applications under the background of computing- network convergence

Architecture and application of computing intelligent broadband network gateway for the AI agent Internet

Related Author

刘尹玥

Related Institution

北京煜金桥通信建设监理咨询有限责任公司

⁰