Privacy-Preserving Multi-Agent Deep Reinforcement Learning for Effective Resource Auction in Multi-Access Edge Computing
Abstract
Multi-access edge computing (MEC) offloads services for mobile users to facilitate the integration of idle cloudlet resources and bring cloud services closer to users. Existing studies have focused primarily on task coordination and resource allocation with strict time constraints, and typically overlooked the potential privacy leakage of users’ participation strategies in MEC. This paper proposes a novel solution to computation offloading and privacy protection in MEC networks using a Multi-agent Deep Deterministic Policy Gradient (MADDPG) framework. Our approach utilizes game theory to encourage computation offloading by modeling the interaction between cloudlets, Data Center Operators (DCOs), and users as a stochastic auction game. We formulate the computation offloading as an auction game with multiple bidders and incomplete information, and use MADDPG to find an optimal solution. To ensure privacy protection, we design a local Differential Privacy (DP) method in the MADDPG algorithm. With an$(\epsilon, \delta)$-DP mechanism, the local DP ensures that the sampled transitions, including the information on users’ actions, states, and corresponding rewards, are protected from exploitation. Analyses corroborate the effectiveness of our approach in satisfying DP and converging to an equilibrium. Simulations demonstrate the approach achieves 126.75% better quality-of-experience than a knapsack-based benchmark, when there are 60 cloudlets and up to 100 users.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Combining deep learning with MEC enables the system to scale efficiently as the network expands.
“Combining deep learning with MEC enables the system to scale efficiently as the network expands16.”
From Blockchain-based secure MEC model for VANETs using hybrid networks (2025) · cites this paper as [16]
Cites
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856 · see citing works
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., & Mordatch, I. (2017) · arXiv · doi:10.48550/arxiv.1706.02275 · Cited by 3,377 · see citing works
An Efficient Ascending-Bid Auction for Multiple Objects
Ausubel, L. M. (2004) · American Economic Review · doi:10.1257/0002828043052330 · Cited by 752 · see citing works
The composition theorem for differential privacy
Kairouz, P., Oh, S., & Viswanath, P. (2017) · IEEE Transactions on Information Theory · doi:10.1109/tit.2017.2685505 · Cited by 408 · see citing works
Serghiou, D., Khalily, M., Brown, T., & Tafazolli, R. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3205505 · Cited by 318 · see citing works
Machine and Deep Learning for Resource Allocation in Multi-Access Edge Computing: A Survey
Djigal, H., Xu, J. H., Liu, L., & Zhang, Y. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3199544 · Cited by 173 · see citing works
Deep Learning With Gaussian Differential Privacy
Bu, Z., Dong, J., Long, Q., & Wei-Jie, S. (2020) · Harvard Data Science Review · doi:10.1162/99608f92.cfc5dd25 · Cited by 172 · see citing works
Price and Risk Awareness for Data Offloading Decision-Making in Edge Computing Systems
Mitsis, G., Tsiropoulou, E. E., & Papavassiliou, S. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3188997 · Cited by 121 · see citing works
The Security and Privacy of Mobile-Edge Computing: An Artificial Intelligence Perspective
Wang, C. Q., Yuan, Z., Zhou, P., Xu, Z., Li, R., & Wu, D. O. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3304318 · Cited by 115 · see citing works
Maschler, M., Solan, E., & Zamir, S. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108636049 · Cited by 107 · see citing works
Reinforcement Learning-Based Physical Cross-Layer Security and Privacy in 6G
Lu, X., Xiao, L., Li, P., Ji, X., Xu, C., Yu, S., & Zhuang, W. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3224279 · Cited by 105 · see citing works
Differential Privacy for Functions and Functional DataPreprint
Hall, R., Rinaldo, A., & Wasserman, L. (2012) · arXiv (Cornell University) · doi:10.1184/r1/6586565 · Cited by 91 · see citing works
Intelligent Resource Allocation for Edge-Cloud Collaborative Networks: A Hybrid DDPG-D3QN Approach
Hu, H., Wu, D., Zhou, F., Zhu, X., Hu, R. Q., & Zhu, H. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3253905 · Cited by 85 · see citing works
Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning
Yuan, X., Ni, W., Ding, M., Wei, K., Li, J., & Poor, H. V. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3258255 · Cited by 82 · see citing works
Self-citationGoverning energy consumption in Hadoop through CPU frequency scaling: An analysis
Ibrahim, S., Phan, T.-D., Carpen-Amarie, A., Chihoub, H.-E., Moise, D. M., & Antoniu, G. (2015) · Future Generation Computer Systems · doi:10.1016/j.future.2015.01.005 · Cited by 76 · see citing works
Location Privacy-Aware Task Offloading in Mobile Edge Computing
Wang, Z., Sun, Y., Liu, D., Hu, J., Pang, X., Hu, Y., & Ren, K. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3254553 · Cited by 67 · see citing works
Seid, A. M., Erbad, A., Abishu, H. N., Albaseer, A. M., Abdallah, M. M., & Guizani, M. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3262242 · Cited by 61 · see citing works
Abedin, S. F., Mahmood, A., Tran, N. H. K., Han, Z., & Gidlund, M. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3188217 · Cited by 58 · see citing works
Wan, K., Wu, D., Li, B., Gao, X., Hu, Z., & Chen, D. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22778 · Cited by 55 · see citing works
Optimal Auctions through Deep Learning: Advances in Differentiable Economics
Dütting, P., Feng, Z., Narasimhan, H., Parkes, D. C., & Ravindranath, S. S. (2023) · Journal of the ACM · doi:10.1145/3630749 · Cited by 46 · see citing works
Privacy-Aware Multiagent Deep Reinforcement Learning for Task Offloading in VANET
Wei, D., Zhang, J., Shojafar, M., Kumari, S., Xi, N., & Ma, J. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3202196 · Cited by 37 · see citing works
Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces
Wang, B., & Hegde, N. (2019) · neural information processing systems · Cited by 34 · see citing works
Revisiting the foundations of dominant-strategy mechanisms
Chen, Y.-C., & Li, J. (2018) · Journal of Economic Theory · doi:10.1016/j.jet.2018.10.001 · Cited by 33 · see citing works
Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning
Naderializadeh, N., Sydir, J. J., Simsek, M., & Nikopour, H. (2020) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc48557.2020.9154250 · Cited by 30 · see citing works
Secure Hot Path Crowdsourcing With Local Differential Privacy Under Fog Computing Architecture
Yang, M., Tjuawinata, I., Lam, K. Y., Zhao, J., & Sun, L. (2020) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2020.3039336 · Cited by 30 · see citing works
Mobile Data Offloading with Uniform Pricing and Overlaps
Li, M., Quek, T. Q. S., & Courcoubetis, C. (2018) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2018.2832638 · Cited by 29 · see citing works
Local Differential Privacy for Regret Minimization in Reinforcement LearningPreprint
Garcelon, E., Perchet, V., Pike-Burke, C., & Pirotta, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.07778 · Cited by 24 · see citing works
Distributed privacy protection strategy for MEC enhanced wireless body area networks
Yan, Z., & Liu, H. (2019) · Digital Communications and Networks · doi:10.1016/j.dcan.2019.08.007 · Cited by 21 · see citing works
Uniform price auctions with a last accepted bid pricing rule
Burkett, J. E., & Woodward, K. (2019) · Journal of Economic Theory · doi:10.1016/j.jet.2019.104954 · Cited by 21 · see citing works
Joint Wireless Source Management and Task Offloading in Ultra-Dense Network
Pang, S., & Wang, S. (2020) · IEEE Access · doi:10.1109/access.2020.2980032 · Cited by 17 · see citing works
On the Auction-Based Resource Trading for a Small-Cell Caching System
You, F., Li, J., Lu, J., & Shu, F. (2017) · IEEE Communications Letters · doi:10.1109/lcomm.2017.2690428 · Cited by 15 · see citing works
Self-citationWu, C., Sheng, J., Wang, Y., & Ai, B. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3329003 · Cited by 13 · see citing works
Computational Performance of Deep Reinforcement Learning to Find Nash Equilibria
Graf, C., Zobernig, V., Schmidt, J., & Klöckl, C. (2023) · Computational Economics · doi:10.1007/s10614-022-10351-6 · Cited by 12 · see citing works
Odeyomi, O. T., Tankard, E., & Rawat, D. B. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3325815 · Cited by 11 · see citing works
A Novel Privacy-Preserving Incentive Mechanism for Multi-Access Edge Computing
You, F., Yuan, X., Ni, W., & Jamalipour, A. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3391303 · Cited by 11 · see citing works
Self-citationOnline computation offloading for deadline-aware tasks in edge computing
He, X., Zheng, J., He, Q., Dai, H., Liu, B., Dou, W., & Chen, G. (2022) · Wireless Networks · doi:10.1007/s11276-021-02864-z · Cited by 9 · see citing works
Learning-Based Privacy-Preserving Computation Offloading in Multi-Access Edge Computing
You, F., Yuan, X., Ni, W., & Jamalipour, A. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437967 · Cited by 5 · see citing works
Self-citationBidder Subset Selection Problem in Auction Design
Bei, X., Gravin, N., Lu, P., & Tang, Z. G. (2023) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611977554.ch147 · Cited by 5 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Cui, Q., You, X., Ni, W., Nan, G., Zhang, X., Zhang, J., Lyu, X., Ai, M., Tao, X., Feng, Z., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4337-1 · Cited by 244 · see citing works
Self-citationFrom 5G to 6G: A Survey on Security, Privacy, and Standardization Pathways
Yang, M., Qu, Y., Ranbaduge, T., Thapa, C., Sultan, N. H., Ding, M., Suzuki, H., Ni, W., Abuadbba, A., Smith, D. B., et al. (2025) · ACM Computing Surveys · doi:10.1145/3785467 · Cited by 29 · see citing works
Self-citationDRESS: Diffusion Model-Based Reward Shaping Scheme for Intelligent Networks
You, F., Du, H., Hou, X., Ren, Y., & Huang, K. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3623239 · Cited by 9 · see citing works
Self-citationSun, W., & Yuan, J. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3647586 · Cited by 7 · see citing works
Blockchain-based secure MEC model for VANETs using hybrid networks
Goud, G. V., Arunachalam, R., Shukla, S. K., Saranya, K., Venugopal, S., & Palanisamy, P. (2025) · Scientific Reports · doi:10.1038/s41598-025-27682-7 · Cited by 8 · see citing works
Hong, Z., Wei, X., Zhan, Y., Liu, Y., & Qiu, T. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111664 · Cited by 4 · see citing works
A Novel Indicator for Quantifying and Minimizing Information Utility Loss of Robot Teams
Zhao, X., Cui, Q., Ni, W., Sheng, Q. Z., Jamalipour, A., Nan, G., Tao, X., & Zhang, P. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3574584 · Cited by 2 · see citing works
Self-citationDistributed Privacy-Preserving Reinforcement Learning via Sparse Matrix Encryption for IoT
Ji, T., Liang, Y., Tao, Y., Kong, F., Ge, C., Qin, B., & Yu, J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3638777
Hu, S., Yuan, X., Li, K., Ni, W., & Wang, X. (2025) · doi:10.1002/9781394369485.biblio
Self-citationWang, Z., Xia, X., Khalil, I., Lan, T., Liu, F., Xu, X., Yi, X., Xue, M., & Bertino, E. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3705464
Fang, J., Yan, S., Yin, X., Yu, Y., Tian, C., & Liu, J. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3706546
DPTAG: Game-Theoretic Private Resource Allocation for Internet of Vehicles
Yin, L., Zhang, L., Liang, H., Li, Y., & Long, Q. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3715365
Kokkinakis, P., Soumplis, P., & Varvarigos, E. (2026) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid68966.2026.00068
Feng, J., Zou, S., Liwang, M., Li, K., Ni, W., & Jamalipour, A. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3725070
Self-citationHuang, X., Chen, X., Zhong, W., Kang, J., Li, X., & Wu, Y. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3734993
- Authors
- You, F., Yuan, X., Ni, W., & Jamalipour, A.
- Affiliations
- The University of Sydney (AU)
- Data61 (AU)
- Venue
- IEEE Transactions on Cognitive Communications and Networking
- Published
- 2025-06
- Volume
- 11
- Issue
- 3
- Pages
- 1887-1901
- ISSN
- 2332-7731 (ISSN-L)
- 2372-2045
- OpenAlex
- W4404576838
- Cited by
- 15
- References
- 38
- Citations by year
- 2026: 6 · 2025: 9
- FWCI
- 2.50
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Cognitive Communications and Networking (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Keywords
- mobile edge computing, computation offloading, privacy preservation, differential privacy, multi-agent deep reinforcement learning, MADDPG, auction game, incomplete information, cloudlets, data center operators, quality of experience
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
