Anonymization of location data does not work: a large-scale measurement study

By Hui Zang, Jean-Chrysostome Bolot. 2011

417 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science, Transportation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

In Transportation

Citations in the corpus

Knock Knock, Who's There? Membership Inference on Aggregate Location Data (2017, background): “Previous location privacy research taking into account traces or profiles of single users [7, 12, 16, 24, 28, 37] does not apply to our problem, which focuses on aggregate location statistics.”
The application of differential privacy to health data (2012, background): “The problem with this technique is that the usage of a data independent generalization may result in poor utility, in [47] the authors argue that adding a random sampling step impacts the utility of the data as well.”
Human mobility modeling at metropolitan scales (2012, background): “Finally, Zang and Bolot [35] showed that releasing anonymized CDRs in its original format poses serious privacy risks, as a large fraction of the population could be re-identified from the anonymous data.”
DP-WHERE: Differentially private modeling of human mobility (2013, background): “Several recent papers have characterized the privacy risks of releasing location data, in each case demonstrating the ability to re-identify individual information from geospatial data sets [11, 23, 31].”
Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP (2021, neutral): “There is also a fundamental tradeoff between data utility and the privacy it affords: any anonymisation technique necessarily removes information from data, which may signiﬁcantly decrease its utility (Brickell and Shmatikov, 2008; Zang and Bolot, 2011).”
Unique in the Crowd: The privacy bounds of human mobility (2013, methodology): “In another, mobile phone data have been re-identified using users’ top locations 28 .”
Trajectory Recovery From Ash: User Privacy Is NOT Preserved in Aggregated Mobility Data (2017, background): “[17] and [18] tried to generalize or even permute the original mobility records before anonymization.”
Differentially Private Filtering (2012, background): “Emerging traffic monitoring systems using position measurements from smartphones [6] is another application area where individual position traces can be reidentified by correlating them with public information such as a person’s location of residence or work [6], [7].”
Predicting Users' Motivations behind Location Check-Ins and Utility Implications of Privacy Protection Mechanisms (2015, neutral): “, complete location trace, co-travelers, activities) [7], [30], [35].”
What Does The Crowd Say About You? Evaluating Aggregation-based Location Privacy (2017, background): “Alas, this is ineffective, as location data is inherently unique to the user, and the identities of the subjects generating the traces can often be recovered [11, 20, 52].”
The Tyranny of Data? The Bright and Dark Sides of Data-Driven Decision-Making for Social Good (2016, background): “For example, Zang et al. [98] have reported that if home and work addresses were available for some users, up to 35% of users of the mobile network could be de-identiﬁed just using the two most visited towers, likely to be related to their home and work location.”
Quantifying and protecting location privacy (2015, neutral): “In few cases, that privacy vulnerabilities of sharing location data is discussed, location privacy is evaluated as the anonymity of users [3, 6, 17, 29].”
Study : Privacy Preserving Release of Spatio-temporal Density in Paris (2014, background): “Several recent studies have demonstrated the privacy risks of releasing location data by re-identifying individuals from geospatial data sets [8, 28, 13].”