Achieving dynamic privacy measurement and protection based on reinforcement learning for mobile edge crowdsensing of IoT

Abstract

With the maturity and development of 5G field, Mobile Edge CrowdSensing (MECS), as an intelligent data collection paradigm, provides a broad prospect for various applications in IoT. However, sensing users as data uploaders lack a balance between data benefits and privacy threats, leading to conservative data uploads and low revenue or excessive uploads and privacy breaches. To solve this problem, a Dynamic Privacy Measurement and Protection (DPMP) framework is proposed based on differential privacy and reinforcement learning. Firstly, a DPM model is designed to quantify the amount of data privacy, and a calculation method for personalized privacy threshold of different users is also designed. Furthermore, a Dynamic Private sensing data Selection (DPS) algorithm is proposed to help sensing users maximize data benefits within their privacy thresholds. Finally, theoretical analysis and ample experiment results show that DPMP framework is effective and efficient to achieve a balance between data benefits and sensing user privacy protection, in particular, the proposed DPMP framework has 63% and 23% higher training efficiency and data benefits, respectively, compared to the Monte Carlo algorithm.

Keywords

Mobile edge crowdsensing / Dynamic privacy measurement / Personalized privacy threshold / Privacy protection / Reinforcement learning

References

[1] E. Luo, M.Z.A. Bhuiyan, G. Wang, et al., Privacyprotector: privacy-protected patient data collection in IoT-based healthcare systems, IEEE Commun. Mag. 56 (2) (2018) 163-168.

[2] C. Luo, J. Ji, Q. Wang, et al., Channel state information prediction for 5G wireless communications: a deep learning approach, IEEE Trans. Network Sci. Eng. 7 (2020) 227-236.

[3] H. Ma, D. Zhao, P. Yuan, Opportunities in mobile crowd sensing, IEEE Commun. Mag. 52 (8) (2014) 29-35.

[4] J. Xiong, X. Chen, Q. Yang, et al., A task-oriented user selection incentive mechanism in edge-aided mobile crowdsensing, IEEE Trans. Network Sci. Eng. 7 (4)(2019) 2347-2360.

[5] Z. Yang, R. Wang, D. Wu, et al., Utm: a trajectory privacy evaluating model for online health monitoring, Digital Commun. Network. 7 (3) (2021) 445-452.

[6] Z. Liu, S. Jiang, P. Zhou, et al., A participatory urban traffic monitoring system: the power of bus riders, IEEE Trans. Intell. Transport. Syst. 18 (10) (2017) 2851-2864.

[7] G. Liu, Q. Yang, H. Wang, et al., Trust assessment in online social networks, IEEE Trans. Dependable Secure Comput. 18 (2) (2021) 994-1007.

[8] Q. Jiang, N. Zhang, J. Ni, et al., Unified biometric privacy preserving three-factor authentication and key agreement for cloud-assisted autonomous vehicles, IEEE Trans. Veh. Technol. 69 (9) (2020) 9390-9401.

[9] C. Zhao, S. Yang, P. Yan, et al., Data quality guarantee for credible caching device selection in mobile crowdsensing systems, IEEE Wireless Commun. 25 (3) (2018) 58-64.

[10] Y. Qu, S. Yu, W. Zhou, et al., Customizable reliable privacy-preserving data sharing in cyber-physical social networks, IEEE Trans. Network Sci. Eng. 8 (1) (2021) 269-281.

[11] L. Song, Y. Miao, J. Weng, et al., Privacy-preserving threshold-based image retrieval in cloud-assisted internet of things, IEEE Internet Things J. (2022), 1-1. https://doi.org/10.1109/JIOT.2022.3142933.

[12] L. Lin, X. Liao, H. Jin, et al., Computation offloading toward edge computing, Proc. IEEE 107 (8) (2019) 1584-1607.

[13] Y. Tian, T. Li, J. Xiong, et al., A blockchain-based machine learning framework for edge services in IIoT, IEEE Trans. Ind. Inf. 18 (3) (2022) 1918-1929.

[14] C. Zhou, A. Fu, S. Yu, et al., Privacy-preserving federated learning in fog computing, IEEE Internet Things J. 7 (11) (2020) 10782-10793.

[15] M. Zhao, L. Chen, J. Xiong, et al., A three-party repeated game model for data privacy in mobile edge crowdsensing of IoT,in:Proceedings of the 2020 EAI International Conference on Mobile Multimedia Communications, EAI, 2020, pp. 1-15.

[16] J. Xiong, M. Zhao, M.Z.A. Bhuiyan, et al., An AI-enabled three-party game framework for guaranteed data privacy in mobile edge crowdsensing of IoT, IEEE Trans. Ind. Inf. 17 (2) (2019) 922-933.

[17] D. Wu, P. Zhang, H. Wang, et al., Node service ability aware packet forwarding mechanism in intermittently connected wireless networks, IEEE Trans. Wireless Commun. 15 (12) (2016) 8169-8181.

[18] M. Zhao, L. Chen, Y. Zhong, et al., A dynamic privacy measurement model and evaluation system for mobile edge crowdsensing, Chin J. Network Information. Security. 7 (1) (2021) 157-166.

[19] J. Kang, Z. Xiong, D. Niyato, et al., Reliable federated learning for mobile networks, IEEE Wireless Commun. 27 (2) (2020) 72-80.

[20] Z. Bao, Y. Lin, S. Zhang, et al., Threat of adversarial attacks on DL-based IoT device identification, IEEE Internet Things J. 9 (11) (2022) 9012-9024.

[21] W. Shi, J. Hu, J. Yan, et al., A privacy measurement method using network structure entropy,in:Proceedings of the 2017 IEEE International Conference on Networking and Network Applications, IEEE, 2017, pp. 147-151.

[22] S. Shaham, M. Ding, B. Liu, et al., Transition-entropy: a novel metric for privacy preservation in location-based services,in:Proceedings of the 2019 IEEE Conference on Computer Communications Workshops, IEEE, 2019, pp. 1-6.

[23] T. Zhang, K. Zhao, M. Yang, et al., Research on privacy security risk assessment method of mobile commerce based on information entropy and markov, Wireless Commun. Mobile Comput. 2020 (2020) 1-11.

[24] R. Ma, X. Chen, H. Liu, et al., Research on user privacy measurement and privacy protection in mobile crowdsensing, Netinfo. Security (8) (2018) 64-72.

[25] X. Li, C. Zhang, T. Jung, et al., Graph-based privacy-preserving data publication,in:Proceedings of the 2016 IEEE International Conference on Computer Communications, IEEE, 2016, pp. 1-9.

[26] Y. Yamaoka, K. Itoh, K-presence-secrecy: practical privacy model as extension of k-anonymity, IEICE Trans. Info Syst. 100 (4) (2017) 730-740.

[27] Y. Yan, X. Hao, W. Wang, A set pair analysis method for privacy metric, Eng. J. Wuhan Univ. 48 (6) (2015) 883-890.

[28] W. Huang, J. Xia, M. Yu, et al., Personal privacy metric based on public social network data, J. Phys. Conf. 1087 (3) (2018) 1-12.

[29] X. Liu, B. Yang, X. Jiang, et al., On social-aware data uploading study of D2D-enabled cellular networks, Comput. Network. 166 (2020) 1-14.

[30] G. Sun, X. Xing, X. Qin, Energy harvesting-based data uploading for internet of things, EURASIP J. Wirel. Commun. Netw. 2019 (1) (2019) 1-13.

[31] R. Messaoud, N. Sghaier, M. Moussa, et al., Privacy preserving utility-aware mechanism for data uploading phase in participatory sensing, IEEE Trans. Mobile Comput. 18 (9) (2018) 2160-2173.

[32] J. Xiong, R. Ma, L. Chen, et al., A personalized privacy protection framework for mobile crowdsensing in IIoT, IEEE Trans. Ind. Inf. 16 (6) (2019) 4231-4241.

[33] Z. Cai, X. Zheng, A private and efficient mechanism for data uploading in smart cyber-physical systems, IEEE Trans. Network Sci. Eng. 7 (2) (2018) 766-775.

[34] L. Wang, D. Zhang, Z. Yan, et al., Effsense: a novel mobile crowd-sensing framework for energy-efficient and cost-effective data uploading, IEEE Trans. Syst. Man. Cybernet.: Systems 45 (12) (2015) 1549-1563.

[35] M. Hassan, M. Rehmani, J. Chen, Differential privacy techniques for cyber physical systems: a survey, IEEE Commun. Survey Tutorial 22 (1) (2019) 746-789.

[36] J. He, L. Cai, X. Guan, Differential private noise adding mechanism and its application on consensus algorithm, IEEE Trans. Signal Process. 68 (2020) 4069-4082.

[37] Y. Ge, F. Zhu, X. Ling, et al., Safe q-learning method based on constrained markov decision processes, IEEE Access 7 (2019) 165007-165017.

[38] W. He, Y. Zeng, G. Li, A novel structural reliability analysis method via improved maximum entropy method based on nonlinear mapping and sparse grid numerical integration, Mech. Syst. Signal Process. 133 (2019) 1-21.

[39] M. Xie, C. Peng, R. Wu, et al., Privacy and data utility metric model for structured data, Appl. Res. Comput. 37 (2020) 1465-1473, 05.

[40] A. Lazaric, M. Restelli, A. Bonarini, Reinforcement learning in continuous action spaces through sequential Monte Carlo methods, in: Proceedings of the 2007 MIT International Conference on Neural Information Processing Systems, MIT, 2007, pp. 833-840.