Unique in the shopping mall: On the reidentifiability of credit card metadata

By Y. de Montjoye, Laura Radaelli, V. Singh, Alex Pentland. Science, 2015

541 citations recorded by the source corpus.

Large-scale data sets of human behavior have the potential to fundamentally transform the way we fight diseases, design cities, or perform research. Metadata, however, contain sensitive information. Understanding the privacy of these data sets is key to their broad use and, ultimately, their impact. We study 3 months of credit card records for 1.1 million people and show that four spatiotemporal points are enough to uniquely reidentify 90% of individuals. We show that knowing the price of a transaction increases the risk of reidentification by 22%, on average. Finally, we show that even data sets that provide coarse information at any or all of the dimensions provide little anonymity and that women are more reidentifiable than men in credit card metadata.

Subfields: Artificial Intelligence, Sociology and Political Science, Transportation

View Paper: https://www.semanticscholar.org/paper/cd8e52e8406e90cc3407f8c9d8d78284ddca7ef0

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

Challenges in administrative data linkage for research (2017, background): “However, it is increasingly clear that full anonymization of individual-level data is virtually impossible whilst retaining sufficient granularity for research (de Montjoye et al., 2015).”
Trajectory Recovery From Ash: User Privacy Is NOT Preserved in Aggregated Mobility Data (2017, background): “Keywords Trajectory privacy; aggregated mobility data; statistic data privacy”
Driving forces and barriers of Industry 4.0: Do multinational and small and medium-sized companies have equal opportunities? (2019, background): “For example, de Montjoye et al. (2015) emphasized the risk of re-identification.”
Differential Privacy Techniques for Cyber Physical Systems: A Survey (2018, methodology): “Furthermore, the weaknesses of simply anonymized data was confirmed further by a test carried out on credit card transactions [25], and researchers re-identified”
Left to Other Peoples’ Devices? A Political Economy Perspective on the Big Data Revolution in Development (2017, background): “…12 For a critical treatment of such top-down development, see Chambers (1997); Hart (2001); Heeks (2008); Mosse (2005, 2011). telecommunication firms and released in an anonymized form are still vulnerable to reidentification (de Montjoye et al., 2015).”
Secure, privacy-preserving and federated machine learning in medical imaging (2020, background): “Such re-identification attacks 39 have been shown to yield high success rates both with tabular data 40,41 (such as patient records) and medical imaging data 42 .”