Geo-Indistinguishability를 활용한 위치 기반 서비스에서의 프라이버시 보존 사용자 분포도 예측 = Privacy-Preserving Estimation of Users‘ Density Distribution in Location-based Services through Geo-indistinguishability

다국어 초록 (Multilingual Abstract)

With the development of mobile devices and global positioning systems, various location-based services can be utilized, which collects user's location information and provides services based on it. In this process, there is a risk of personal sensitive information being exposed to the outside, and thus Geo-indistinguishability (Geo-Ind), which protect location privacy of LBS users by perturbing their true location, is widely used. However, owing to the data perturbation mechanism of Geo-Ind, it is hard to accurately obtain the density distribution of LBS users from the collection of perturbed location data.
Thus, in this paper, we aim to develop a novel method which enables to effectively compute the user density distribution from perturbed location dataset collected under Geo-Ind. In particular, the proposed method leverages Expectation-Maximization(EM) algorithm to precisely estimate the density disribution of LBS users from perturbed location dataset. Experimental results on real world datasets show that our proposed method achieves significantly better performance than a baseline approach.

국문 초록 (Abstract)

최근 들어 모바일 디바이스와 GPS(Global Positioning System)의 발전으로 다양한 위치 기반 서비스(Location-Based Servises, LBS)를 활용할 수 있게 되었다. LBS 사용자는 서비스를 이용하기 위해 자신의 위치 정보를 서비스 제공자에게 노출한다. 이 과정에서 개인의 민감한 정보를 침해할가능성이 있으므로 사용자의 위치 데이터를 변조하여 프라이버시를 보존할 수 있는Geo-indistinguishability(Geo-Ind) 기법이 많이 활용되고 있다. 그러나 Geo-Ind 기법으로 인하여 사용자로부터 변조된 데이터를 수집하는 경우, LBS 제공자는 사용자 분포에 대한 정확한 정보를 얻을수 없다. 그러므로 본 논문에서는 Geo-Ind 기법을 이용하여 사용자로부터 수집한 변조된 위치 데이터로부터 사용자 분포에 대한 정보를 정확하게 계산하기 위한 방법을 제안한다. 특히, Expectation-Maximization(EM) 기법을 이용하여 변조된 데이터로부터 사용자의 위치 분포를 정확하게 예측하기 위한 기법을 제안한다. 또한 실제 데이터를 이용해 제안 기법의 우수성을 입증한다.

참고문헌 (Reference)

• 1 남지연 ; 나종연, "소비자의 위치정보 프라이버시 침해에 대한 우려와 위치기반서비스 사용에 관한 연구" 한국소비자정책교육학회 5 (5): 81-102, 2009
• 2 J. W. Kim, "Workload-aware indoor positioning data collection via local differential privacy" 23 (23): 1352-1356, 2019
• 3 Oliva J., "Transformation Autoregressive Networks" 80 : 3898-3907, 2018
• 4 Fakoor R., "TradE:Transformers for Density Estimation"
• 5 T. K. Moon, "The expectation-maximization algorithm" 13 (13): 47-60, 1996
• 6 Ng, S.K, "The EM Algorithm" Springer 2011
• 7 Yu Zheng, "T-Drive trajectory data sample"
• 8 U. Erlingsson, "RAPPOR: Randomized aggregatable privacy-preserving ordinal response" 1054-1067, 2014
• 9 Kido H, "Protection of Location Privacy Using Dummies for Location-based Services" 1248-1248, 2005
• 10 N. E. Bordenabe, "Optimal geo-indistinguishable mechanisms for location privacy" 251-262, 2014
• 11 Chawla S., "On the Utility of Privacy-Preserving Histograms" 2005
• 12 Huang C. -W., "Neural Autoregressive Flows" 80 : 2078-2087, 2018
• 13 Ma C, "Nearby friend discovery with geo-indistinguishability to stalkers" 34 : 352-359, 2014
• 14 Papamakarios G., "Masked Autoregressive Flow for Density Estimation" 30 : 2338-2347, 2017
• 15 Wang L, "Location Privacy-preserving Task Allocation for Mobile Crowdsensing with Differential Geo-obfuscation" 627-636, 2017
• 16 Bojan Jovanovic, "Internet of Things statistics for 2022 - Taking Things Apart"
• 17 Kingma D. P., "Improved Variational Inference with Inverse Autoregressive Flow" 29 : 4743-4751, 2016
• 18 Xue M, "I Know Where You Are:Thwarting Privacy Protection in Location-based Social Discovery Services" 179-184, 2015
• 19 M. E. Andres, "Geo-indistinguishability: Differential privacy for location-based systems" 901-914, 2013
• 20 Elad Tzoreff, "Expectation-maximization algorithm for direct position determination" 133 : 32-39, 2016
• 21 K. Chatzikokolakis, "Efficient utility improvement for location privacy" 210-231, 2017
• 22 Huang C, "EPPD:Efficient and Privacy-preserving Proximity Testing with Differential Privacy Techniques" 1-6, 2016
• 23 Pan X, "DistSD: Distance-based Social Discovery with Personalized Posterior Screening" 1110-1119, 2016
• 24 C. Dwork, "Differential privacy" 1-12, 2006
• 25 J. W. Kim, "Collecting health lifelog data from smartwatch users in a privacy-preserving manner" 65 (65): 369-378, 2019
• 26 C. Dwork, "Calibrating noise to sensitivity in private data analysis" 265-284, 2006
• 27 D. Zibar, "Applications of expectation maximization algorithm for coherent optical communication" 1890-1894, 2014
• 28 Kujawińska, A, "Application of expectation maximization metod for purchase decision-making support in welding branch,‖ Management and Production Engineering Review" 7 (7): 29-33, 2016
• 29 Gruteser MO, "Anonymous Usage of Location-based Services through Spatial and Temporal Cloaking" 31-42, 2003
• 30 Matt Kapko, "AT&T, T-Mobile, Sprint seek to make amends over location breach"
• 31 R. Ahuja, "A utility-preserving and scalable technique for protecting location data with geoindistinguishability" 210-231, 2019
• 32 Tong W, "A jointly differentially private scheduling protocol for ridesharing services" 12 (12): 2444-2456, 2017
• 33 Pozi, M.S.M, "A Kernel Density Estimation Method to Generate Synthetic Shifted Datasets in Privacy-Preserving Task" 10 (10): 70-89, 2020