Abstract
With the emergence of technology, there has been a high influx of information over social networks. Cybersecurity is thus the need of the hour. The crux of cybersecurity is network dynamics. Location-specific information over a location-based social network (LBSN) makes every user a discrete target for adversaries as opposed to the social network domain of a traditional network. This further aggravates the problem of POI recommendations. POI recommendation requires the amalgamation of side information and location-specific information for better exploitation of the user’s preference. In this paper, we present a novel approach (DPSND-Rec) Differential Privacy-based Social Network Detection over Spatial–Temporal proximity for POI Recommendation in LBSN. DPSND-Rec consists of three phases. In the first phase, we add Laplacian noise in the historical check-in data of the user and form the visitation profile of the user. Then, we sought the spatial and temporal neighbors of the user using certain similarity measures. While in the third step, we feed the user, POI, and neighbors embeddings in LSTM coupled with Differentially Private Stochastic Gradient Descent (DP-SGD). The approach is evaluated on two real-world datasets with empirical analysis of two metrics: NDCG and accuracy. The results demonstrate enhanced performance over other state-of-art methods.
Similar content being viewed by others
References
Montjoye Y-A, Hidalgo C, Verleysen M, Blondel V. Unique in the crowd: the privacy bounds of human mobility. Sci Rep. 2013;3:1376. https://doi.org/10.1038/srep01376.
Jung G, Lee H, Kim A, Lee U. Too much information: assessing privacy risks of contact trace data disclosure on people with COVID-19 in South Korea. Front Public Health. 2020;8:305. https://doi.org/10.3389/fpubh.2020.00305.
Zhang F, Lee V, Kim-Kwang Raymond R. Jo-DPMF: differentially private matrix factorization learning through joint optimization. Inf Sci. 2018. https://doi.org/10.1016/j.ins.2018.07.070.
Ma X, Li H, Ma J, Jiang Q, Gao S, Xi N, Lu D. APPLET: a privacy-preserving framework for location-aware recommender system. Sci China Inf Sci. 2017. https://doi.org/10.1007/s11432-015-0981-4.
Hyejin S, Kim S, Shin J, Xiao X. Privacy Enhanced Matrix Factorization for Recommendation with Local Differential Privacy. IEEE Trans Knowl Data Eng. 2018. https://doi.org/10.1109/TKDE.2018.2805356.
Heitor W, Silva N, Viana M, Mourão F, Pereira A, Rocha L. A survey on point-of-interest recommendation in location-based social networks. 2020; 185–192. https://doi.org/10.1145/3428658.3430970.
Koren Y. Factorization meets the neighborhood: a multifaceted collaborative filtering model. Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD’08), 2008; 426–34. https://doi.org/10.1145/1401890.1401944
Manas P, Richard C, Runting S, Cong W. Privacy-preserving collaborative filtering. 2013
Daniele R, Bettini C. Private context-aware recommendation of points of interest: an initial investigation. 2012 IEEE International Conference on Pervasive Computing and Communications Workshops, PERCOM Workshops 2012. 2012. https://doi.org/10.1109/PerComW.2012.6197582.
Berkovsky S, Eytani Y, Kuflik T, F Ricci. Enhancing privacy and preserving accuracy of a distributed collaborative filtering. 2007; 9–16. https://doi.org/10.1145/1297231.1297234.
Jeyamohan N, Chen X, Aslam N. Local differentially private matrix factorization for recommendations. 2019; 1–5. https://doi.org/10.1109/SKIMA47702.2019.8982536.
Liu Z, Wang Y-X, Smola A. Fast differentially private matrix factorization. 2015. https://doi.org/10.1145/2792838.2800191.
McSherry F, Mironov I. Differentially private recommender systems: building privacy into the Netflix prize contenders. Differ Private Recommend Syst. 2009;627–36. https://doi.org/10.1145/1557019.1557090
Zekeriya E, Beye M, Veugen T, Lagendijk R. Privacy enhanced recommender system. 2010
Nikolaenko V, Ioannidis S, Weinsberg U, Joye M, Taft N, Boneh D. Privacy-preserving matrix factorization. Proc ACM Conf Comput Commun Secur. 2013. https://doi.org/10.1145/2508859.2516751.
Wang M, Lei H, Li S. A geographical and social society attributes based privacy preserving recommendation method for POIs. Secur Commun Netw. 2022. https://doi.org/10.1155/2022/4262814.
Chen R, Fung BC, Mohammed N, Desai BC, Wang K. Privacy-preserving trajectory data publishing by local suppression. Inf Sci. 2013;231:83–97.
Badsha S, Yi X, Khalil I, Bertino E. Privacy preserving user-based recommender system. 2017; 1074–83. https://doi.org/10.1109/ICDCS.2017.248.
Erlingsson Ú, Korolova A, Pihur V. RAPPOR: randomized aggregatable privacy-preserving ordinal response. Proc ACM Conf Comput Commun Secur. 2014. https://doi.org/10.1145/2660267.2660348.
Differential Privacy Team. Learning with privacy at scale. Apple Mach Learn J. 2017;1(8):1–25.
Ding B, Kulkarni J, Yekhanin S. Collecting telemetry data privately. In NIPS, 2017; pp. 3571–80.
Nguyên TT, Xiao X, Yang Y, Hui SC, Shin H, Shin J. Collecting and analyzing data from smart device users with local differential privacy. arXiv preprint, 2016; arXiv:1606.05053.
Hua J, Xia C, Zhong S. Differentially private matrix factorization. In IJCAI, 2015; p. 1763–70.
Zhang S, Liu L, Chen Z, Zhong H. Probabilistic matrix factorization with personalized differential privacy. Knowl-Based Syst. 2019. https://doi.org/10.1016/j.knosys.2019.07.035.
Shin H, Kim S, Shin J, Xiao X. Privacy enhanced matrix factorization for recommendation with local differential privacy. IEEE Trans Knowl Data Eng. 2018. https://doi.org/10.1109/TKDE.2018.2805356.
Kim JS, Kim J, Chung Y. Successive point-of-interest recommendation with local differential privacy. IEEE Access. 2021;9:66371–86. https://doi.org/10.1109/ACCESS.2021.3076809.
Khan MM, Ibrahim R, Ghani I. Cross domain recommender systems: a systematic literature review. ACM Comput Surv. 2017;50:1–34. https://doi.org/10.1145/3073565.
Liu A, Wang W, Li Z, Liu G, Li Q, Zhou X, Zhang X. A privacy-preserving framework for trust-oriented point-of-interest recommendation. IEEE Access. 2017. https://doi.org/10.1109/ACCESS.2017.2765317.
Xu C, Zhu L, Liu Y, Guan J, Yu S. DP-LTOD: differential privacy latent trajectory community discovering services over location-based social networks. IEEE Trans Serv Comput. 2018. https://doi.org/10.1109/TSC.2018.2855740.
Li G, Yin G, Xiong Z, Chen F. CGPP-POI: a recommendation model based on privacy protection. Wirel Commun Mob Comput. 2021;2021:1–20. https://doi.org/10.1155/2021/4873574.
Long J, Chen T, Hung N, Yin H. Decentralized collaborative learning framework for next POI recommendation. ACM Trans Inf Syst. 2022. https://doi.org/10.1145/3555374.
Perifanis V, Drosatos G, Stamatelatos G, Efraimidis PS. FedPOIRec: privacy-preserving federated poi recommendation with social influence. Inf Sci. 2023;623:767–90.
Waters N. Tobler’s first law of geography. 2017; https://doi.org/10.1002/9781118786352.wbieg1011.
Qian T-Y, Liu B, Hong L, You Z-N. Time and location aware points of interest recommendation in location-based social networks. J Comput Sci Technol. 2018;33:1219–30. https://doi.org/10.1007/s11390-018-1883-7.
Dai S, Yu Y, Fan H, Dong J. Spatio-temporal representation learning with social tie for personalized POI recommendation. Data Sci Eng. 2022. https://doi.org/10.1007/s41019-022-00180-w.
Ma C, Zhang Y, Wang Q, Liu X. Point-of-interest recommendation: exploiting self-attentive autoencoders with neighbor-aware influence. 2018; 697–706. https://doi.org/10.1145/3269206.3271733.
Li M, Zheng W, Xiao Y, Zhu K, Huang W. Exploring temporal and spatial features for next POI recommendation in LBSNs. IEEE Access. 2021;9:35997–6007. https://doi.org/10.1109/ACCESS.2021.3061502.
Guo T, Luo J, Dong K, Yang M. Locally differentially private item-based collaborative filtering. Inf Sci. 2019;502:229–46.
Shin H, Kim S, Shin J, Xiao X. Privacy enhanced matrix factorization for recommendation with local differential privacy. IEEE Trans Knowl Data Eng. 2018;30(9):1770–82.
Funding
Not applicable.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors of the manuscript state that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the topical collection “Cyber Security and Privacy in Communication Networks” guest edited by Rajiv Misra, R K Shyamsunder, Alexiei Dingli, Natalie Denk, Omer Rana, Alexander Pfeiffer, Ashok Patel and Nishtha Kesswani.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Acharya, M., Mohbey, K.K. Differential Privacy-Based Social Network Detection Over Spatio-Temporal Proximity for Secure POI Recommendation. SN COMPUT. SCI. 4, 252 (2023). https://doi.org/10.1007/s42979-023-01683-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-023-01683-7