Quasi-identifier
Quasi-identifiers are pieces of information that are not of themselves unique identifiers, but are sufficiently well correlated with an entity that they can be combined with other quasi-identifiers to create a unique identifier.[1]
Quasi-identifiers can thus, when combined, become personally identifying information. This process is called re-identification. As an example, Latanya Sweeney has shown that even though neither gender, birth dates nor postal codes uniquely identify an individual, the combination of all three is sufficient to identify 87% of individuals in the United States.[2]
The term was introduced by Tore Dalenius in 1986.[3] Since then, quasi-identifiers have been the basis of several attacks on released data. For instance, Sweeney linked health records to publicly available information to locate the then-governor of Massachusetts' hospital records using uniquely identifying quasi-identifiers,[4][5] and Sweeney, Abu and Winn used public voter records to re-identify participants in the Personal Genome Project.[6] Additionally, Arvind Narayanan and Vitaly Shmatikov discussed on quasi-identifiers to indicate statistical conditions for de-anonymizing data released by Netflix.[7]
Motwani and Ying warn about potential privacy breaches being enabled by publication of large volumes of government and business data containing quasi-identifiers.[8]
See also
- De-identification
- Differential privacy
- Personally identifying information
References
- ^ "Glossary of Statistical Terms: Quasi-identifier". OECD. November 10, 2005. Retrieved 29 September 2013.
- ^ Sweeney, Latanya. Simple demographics often identify people uniquely. Carnegie Mellon University, 2000. http://dataprivacylab.org/projects/identifiability/paper1.pdf
- ^ Dalenius, Tore. Finding a Needle In a Haystack or Identifying Anonymous Census Records. Journal of Official Statistics, Vol.2, No.3, 1986. pp. 329–336. http://www.jos.nu/Articles/abstract.asp?article=23329 Archived 2017-08-08 at the Wayback Machine
- ^ Anderson, Nate. Anonymized data really isn’t—and here’s why not. Ars Technica, 2009. https://arstechnica.com/tech-policy/2009/09/your-secrets-live-online-in-databases-of-ruin/
- ^ Barth-Jones, Daniel C. The're-identification'of Governor William Weld's medical information: a critical re-examination of health data identification risks and privacy protections, then and now. Then and Now (June 4, 2012) (2012).
- ^ Sweeney, Latanya, Akua Abu, and Julia Winn. "Identifying participants in the personal genome project by name." Available at SSRN 2257732 (2013).
- ^ Narayanan, Arvind and Shmatikov, Vitaly. Robust De-anonymization of Large Sparse Datasets. The University of Texas at Austin, 2008. https://www.cs.utexas.edu/~shmat/shmat_oak08netflix.pdf
- ^ Rajeev Motwani and Ying Xu (2008). Efficient Algorithms for Masking and Finding Quasi-Identifiers (PDF). Proceedings of SDM’08 International Workshop on Practical Privacy-Preserving Data Mining.
- v
- t
- e