Intelligent Privacy-Aware Computation Offloading Method Against Multi-Server Joint Inference Attacks

MIN Minghui; LIU Mingcheng; ZHANG Peng; DUAN Jincheng; LI Shiyin; ZHANG Hongliang

doi:10.11999/JEIT260249

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2026 >

MIN Minghui, LIU Mingcheng, ZHANG Peng, DUAN Jincheng, LI Shiyin, ZHANG Hongliang. Intelligent Privacy-Aware Computation Offloading Method Against Multi-Server Joint Inference Attacks[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260249

Citation:

MIN Minghui, LIU Mingcheng, ZHANG Peng, DUAN Jincheng, LI Shiyin, ZHANG Hongliang. Intelligent Privacy-Aware Computation Offloading Method Against Multi-Server Joint Inference Attacks[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260249

Citation:

MIN Minghui, LIU Mingcheng, ZHANG Peng, DUAN Jincheng, LI Shiyin, ZHANG Hongliang. Intelligent Privacy-Aware Computation Offloading Method Against Multi-Server Joint Inference Attacks[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260249

PDF( 3515 KB)

Intelligent Privacy-Aware Computation Offloading Method Against Multi-Server Joint Inference Attacks

doi: 10.11999/JEIT260249 cstr: 32379.14.JEIT260249

1.
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
2.
School of Electronics, Peking University, Beijing 100871, China

Funds: Natural Science Foundation of China (62571529, U25A20388, 62371451), Jiangsu Province Basic Research Special Funds (Natural Science Foundation) (BK20242083), Jiangsu Province Young Scientific and Technological Talent Support Program, (JSTJ-2024-039), Postgraduate Research \& Practice Innovation Program of Jiangsu Province under Grant KYCX25_2841、Graduate Innovation Program of China University of Mining and Technology under Grant 2025WLKXJ104

Received Date: 2026-03-09
Accepted Date: 2026-06-15
Rev Recd Date: 2026-06-15

Available Online: 2026-06-23

Abstract

Abstract

Objective With the rapid advancement of the low-altitude economy, services such as intelligent transportation, smart healthcare, and low-altitude logistics have become increasingly pervasive, the efficient operation of which relies heavily on the real-time processing of massive sensor data. Mobile edge computing (MEC) enhances task execution efficiency and alleviates device computational burdens by offloading tasks to nearby MEC servers. However, user privacy and security threats have become progressively severe. In dynamic scenarios where multiple MEC servers collaboratively process tasks, joint inference attacks via information sharing drastically escalate the risk of user location privacy leakage. Although existing studies have adopted differential privacy (DP) to safeguard user location privacy, DP-based solutions remain insufficient. Existing methods inject noise into offloading decisions to protect privacy, yet unconstrained noise can degrade the accuracy of task allocation. Furthermore, in dynamic computation offloading scenarios, the real-time mobility of users induces continuous dynamics in channel states. Both the privacy leakage risks inherent in task offloading and the behaviors of attackers exhibit significant uncertainties. Traditional optimization theories, relying on static system models, fail to cope with the optimization challenges in such dynamic environments. To overcome these challenges, this paper proposes an Asynchronous Advantage Actor-Critic (A3C)-based intelligent privacy-aware computation offloading (AIPCO) scheme capable of resisting multi-server joint inference attacks. While effectively safeguarding user location privacy, the proposed scheme maximizes the overall utility of the MEC system. Methods This paper proposes a DP-based task offloading rate perturbation mechanism. By introducing controlled noise, the mechanism enhances the randomness of user task offloading toward multiple MEC servers. Concurrently, a truncated Laplace mechanism is utilized to constrain the boundaries of the perturbed offloading rates, thereby strictly satisfying the mathematical guarantees of DP and effectively degrading the accuracy of multi-server cooperative inference attacks in identifying sensitive user locations. On this basis, privacy entropy is introduced to dynamically evaluate the real-time efficacy of privacy protection. Finally, the AIPCO scheme is constructed. Leveraging its multi-threaded asynchronous training mechanism, the scheme interacts with the environment through iterative trial-and-error to efficiently learn the optimal real-time offloading policy online. While dynamically safeguarding user privacy, the proposed scheme minimizes computational overhead, ultimately achieving the maximization of the comprehensive system utility. Results and Discussions The AIPCO scheme achieves simultaneous optimization of user privacy and task offloading costs by strategically incorporating multidimensional performance variables into the reward function of reinforcement learning. A comprehensive multi-dimensional performance analysis of this scheme (Figure 4) indicates that, in terms of dynamic convergence performance, when the continuous learning iterations reach 200, its privacy protection level improves significantly by 2.52%, 3.56%, and 22.90% compared to baseline schemes RCLM, JODRL, and DODA-DT, respectively. This distinct advantage stems directly from AIPCO’s adoption of a DP-based method for perturbing the offloading rate, which successfully utilizes a truncated Laplace mechanism to enhance data randomness while strictly limiting the perturbation range. In sharp contrast, RCLM only perturbs the rate via range-limited DP without implementing a truncated Laplace mechanism; JODRL merely increases randomness through network policy optimization, resulting in lower protection levels; and DODA-DT focuses exclusively on balancing energy consumption and system latency without optimizing user privacy. Regarding the critical privacy weight parameters (Figure 5), systematically increasing $w$ enhances privacy protection. For instance, the privacy protection level improves by 5.64% as the weight rises from 0.2 to 0.7, with the performance gain being particularly significant at a weight of 0.7. As the system proxy reduces its primary focus on computational costs, user benefits remain optimal despite rising expenses. Furthermore, when adjusting the physical distance between users and the MEC server (Figure 6), AIPCO demonstrates superior privacy protection capabilities in long-distance scenarios. Greater distance inherently reduces tasks offloaded to the server; thus, the less information an attacker obtains, the better the privacy protection. Although computational costs inevitably rise with distance, AIPCO consistently outperforms competing schemes, confirming that it achieves optimal benefits for the MEC system while safeguarding user privacy. Conclusions To mitigate joint inference attacks from information sharing among collaborative MEC servers, this paper proposes an intelligent privacy-aware computation offloading method. A DP-based task offloading rate perturbation scheme enhances randomness, using a truncated Laplace mechanism to constrain perturbed rates within reasonable boundaries. While proving the scheme strictly satisfies DP mathematical guarantees, privacy entropy is introduced to quantitatively evaluate privacy protection efficacy. Furthermore, the designed AIPCO scheme leverages a multi-threaded asynchronous training mode, enabling the agent to efficiently learn the optimal perturbed offloading policy within a continuous space to maximize overall system utility. Simulation results demonstrate that the proposed scheme significantly outperforms baselines in both dynamic and average performance, achieving optimal system utility while safeguarding user privacy.
- Mobile Edge Computing,
- Joint Inference Attacks,
- Location Privacy,
- Differential Privacy,
- Asynchronous Advantage Actor-Critic Algorithm

FullText(HTML)

References(27)

References

[1]	胡钰林, 喻鑫岚, 高伟, 等. 低时延工业物联网中移动边缘计算的安全性与可靠性联合优化[J]. 电子与信息学报, 2025, 47(10): 3492–3504. doi: 10.11999/JEIT250262. HU Yulin, YU Xinlan, GAO Wei, et al. Security and reliability-optimal offloading for mobile edge computing in low-latency industrial IoT[J]. Journal of Electronics & Information Technology, 2025, 47(10): 3492–3504. doi: 10.11999/JEIT250262.
[2]	YANG Helin, ZHENG Mengting, SHAO Ziling, et al. Intelligent computation offloading and trajectory planning for 3-D target search in low-altitude economy scenarios[J]. IEEE Wireless Communications Letters, 2025, 14(4): 949–953. doi: 10.1109/LWC.2025.3527005.
[3]	施建锋, 陈忻阳, 李宝龙. 面向物联网的云边端协同计算中任务卸载与资源分配算法研究[J]. 电子与信息学报, 2025, 47(2): 458–469. doi: 10.11999/JEIT240659. SHI Jianfeng, CHEN Xinyang, and LI Baolong. Research on task offloading and resource allocation algorithms in cloud-edge-end collaborative computing for the internet of things[J]. Journal of Electronics & Information Technology, 2025, 47(2): 458–469. doi: 10.11999/JEIT240659.
[4]	闵明慧, 张鹏, 朱浩鹏, 等. 能量收集辅助的矿山物联网智能计算卸载方法[J]. 电子与信息学报, 2023, 45(10): 3547–3557. doi: 10.11999/JEIT220973. MIN Minghui, ZHANG Peng, ZHU Haopeng, et al. Energy harvesting assisted intelligent computation offloading method for the IoT in mining[J]. Journal of Electronics & Information Technology, 2023, 45(10): 3547–3557. doi: 10.11999/JEIT220973.
[5]	LAN Wenjun, CHEN Kongyang, LI Yikai, et al. Deep reinforcement learning for privacy-preserving task offloading in integrated satellite-terrestrial networks[J]. IEEE Transactions on Mobile Computing, 2024, 23(10): 9678–9691. doi: 10.1109/TMC.2024.3366928.
[6]	WANG Zhibo, SUN Yunan, LIU Defang, et al. Location privacy-aware task offloading in mobile edge computing[J]. IEEE Transactions on Mobile Computing, 2024, 23(3): 2269–2283. doi: 10.1109/TMC.2023.3254553.
[7]	MIN Minghui, ZHANG Peng, ZHANG Yue, et al. Personalized location privacy-aware task offloading: A dual-agent DRL approach[J]. IEEE Transactions on Mobile Computing, 2026, 25(4): 5824–5838. doi: 10.1109/TMC.2025.3634361.
[8]	HE Yulong, HE Xiaofan, JIN Richeng, et al. Location privacy-aware and energy-efficient offloading for distributed edge computing[J]. IEEE Transactions on Wireless Communications, 2023, 22(11): 7975–7988. doi: 10.1109/TWC.2023.3257197.
[9]	WU Guowen, CHEN Xihang, GAO Zhengjun, et al. Privacy-preserving offloading scheme in multi-access mobile edge computing based on MADRL[J]. Journal of Parallel and Distributed Computing, 2024, 183: 104775. doi: 10.1016/j.jpdc.2023.104775.
[10]	FANG Juan, QU Dezheng, CHEN Huijie, et al. Dependency-aware dynamic task offloading based on deep reinforcement learning in mobile-edge computing[J]. IEEE Transactions on Network and Service Management, 2024, 21(2): 1403–1415. doi: 10.1109/TNSM.2023.3319294.
[11]	ZHANG Degan, AN Hongzhan, ZHANG Jie, et al. Novel privacy awareness task offloading approach based on privacy entropy[J]. IEEE Transactions on Network and Service Management, 2024, 21(3): 3598–3608. doi: 10.1109/TNSM.2024.3355967.
[12]	LI Peisong, XIAO Ziren, GAO Honghao, et al. Reinforcement learning based edge-end collaboration for multi-task scheduling in 6G enabled intelligent autonomous transport systems[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(10): 17624–17637. doi: 10.1109/TITS.2024.3525356.
[13]	FENG Jun, YANG L T, ZHU Qing, et al. Privacy-preserving tensor decomposition over encrypted data in a federated cloud environment[J]. IEEE Transactions on Dependable and Secure Computing, 2020, 17(4): 857–868. doi: 10.1109/TDSC.2018.2881452.
[14]	DU Miao, LIU Yinqiu, ZHAO Changyuan, et al. GDP-UAV: A Gaussian differential privacy-empowered multi-UAV task offloading in low-altitude economy networks[J]. IEEE Transactions on Cognitive Communications and Networking, 2026, 12: 5001–5013. doi: 10.1109/TCCN.2025.3638768.
[15]	MIN Minghui, DUAN Jincheng, LIU Mingcheng, et al. Task offloading with differential privacy in multi-access edge computing: An A3C-based approach[J]. IEEE Transactions on Cognitive Communications and Networking, 2026, 12: 5676–5689. doi: 10.1109/TCCN.2026.3657108.
[16]	ZHU Bincheng, HUANG Liang, CHI Kaikai, et al. Enhancing energy efficiency in wireless-powered MEC systems through lyapunov-guided deep reinforcement learning[J]. IEEE Transactions on Wireless Communications, 2025, 24(9): 7563–7580. doi: 10.1109/TWC.2025.3561167.
[17]	GAN Shuying, SIEW M, XU Chao, et al. Differentially private deep Q-learning for pattern privacy preservation in MEC offloading[C]. Proceedings of 2023 IEEE International Conference on Communications, Rome, Italy, 2023: 3578–3583. doi: 10.1109/ICC45041.2023.10278840.
[18]	PANG Xiaoyi, WANG Zhibo, LI Jingxin, et al. Towards online privacy-preserving computation offloading in mobile edge computing[C]. Proceedings of 2022-IEEE Conference on Computer Communications, London, UK, 2022: 1179–1188. doi: 10.1109/INFOCOM48880.2022.9796748.
[19]	ZHANG Pengfei, SUN Hong, ZHANG Zhikun, et al. Privacy-preserving recommendations with mixture model-based matrix factorization under local differential privacy[J]. IEEE Transactions on Industrial Informatics, 2025, 21(7): 5451–5459. doi: 10.1109/TII.2025.3555993.
[20]	FENG Jun, YANG L T, NIE Xin, et al. Edge-cloud-aided differentially private tucker decomposition for cyber-physical-social systems[J]. IEEE Internet of Things Journal, 2022, 9(11): 8387–8396. doi: 10.1109/JIOT.2020.3004826.
[21]	DEMIR S, STAPPERS B, KOK K, et al. Statistical arbitrage trading on the intraday market using the asynchronous advantage actor–critic method[J]. Applied Energy, 2022, 314: 118912. doi: 10.1016/j.apenergy.2022.118912.
[22]	方贤进, 甄雅茹, 张朋飞, 等. 本地差分隐私下技能感知的任务分配算法研究[J]. 电子与信息学报, 2025, 47(11): 4429–4439. doi: 10.11999/JEIT250425. FANG Xianjin, ZHEN Yaru, ZHANG Pengfei, et al. Research on skill-aware task assignment algorithm under local differential privacy[J]. Journal of Electronics & Information Technology, 2025, 47(11): 4429–4439. doi: 10.11999/JEIT250425.
[23]	CHEN Jiajun, HU Chunqiang, SHENG Weihong, et al. Sensitivity-aware personalized differential privacy guarantees for online social networks[J]. IEEE Transactions on Information Forensics and Security, 2025, 20: 3116–3130. doi: 10.1109/TIFS.2025.3551642.
[24]	杨淼焱, 方旭明. 车联网中采用混合分层DRL的无人机辅助移动边缘计算[J]. 电子与信息学报, 2026, 48(4): 1668–1677. doi: 10.11999/JEIT250743. YANG Miaoyan and FANG Xuming. UAV-assisted mobile edge computing based on hybrid hierarchical DRL in the internet of vehicular[J]. Journal of Electronics & Information Technology, 2026, 48(4): 1668–1677. doi: 10.11999/JEIT250743.
[25]	HUSSAIN A, AKBAR W, HUSSAIN T, et al. Ensuring zero trust IoT data privacy: Differential privacy in blockchain using federated learning[J]. IEEE Transactions on Consumer Electronics, 2025, 71(1): 1167–1179. doi: 10.1109/TCE.2024.3444824.
[26]	FENG Libo, GUO Junwei, FANG Fake, et al. SEPP-FLBC: A secure and efficient privacy protection scheme using federate learning and blockchain for edge-end-cloud devices[J]. IEEE Transactions on Services Computing, 2026, 19(1): 657–670. doi: 10.1109/TSC.2025.3641964.
[27]	GAN Ying, XIAO Zhanhui, KE Ting, et al. UAV application with XAI and soft computing methods to protect privacy of power-data in smart grids[J]. IEEE Transactions on Consumer Electronics, 2025, 71(2): 3921–3929. doi: 10.1109/TCE.2025.3551519.