Weaving Technology and Policy Together to Maintain Confidentiality

By Latanya Sweeney. 1997

How researchers see this paper

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

Citations in the corpus

Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data (2016, background): “…learning applications with great beneﬁts are enabled only through the analysis of sensitive data, such as users’ personal contacts, private photographs or correspondence, or even medical records or genetic sequences (Alipanahi et al., 2015; Kannan et al., 2016; Kononenko, 2001; Sweeney, 1997).”
On the Difficulties of Disclosure Prevention in Statistical Databases or The Case for Differential Privacy (2010, background): “The work of Agrawal and Srikant [2] and the spectacular privacy compromises achieved by Sweeney [33] rekindled interest in the problem among computer scientists, particularly within the database community.”
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks (2017, background): “…circumstances, re-identiﬁcation of patients can be accomplished through residual distinguishable patterns in various features (e.g., demographics (Sweeney, 1997; El Emam et al., 2011a), diagnoses (Loukides et al., 2010), lab tests (Atreya et al., 2013), visits across healthcare providers (Malin…”
Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression (1998, methodology): “As discussed earlier, ZIP code, date of birth, and gender can be linked to population registers that are publicly available in order to re-identify patients [18].”
Differentially private multi-party computation (2014, background): “Such attacks have revealed the medical record of a former governor of Massachusetts [37], the purchase history of Amazon users[6], genomic information [24], and movie viewing history of Netflix users [33].”
PIR-Tor: Scalable Anonymous Communication Using Private Information Retrieval (2011, background): “In turn, these profiles can lead to the re-identification of users directly [16] or by combining them with publicly available databases [14, 30, 43].”
Robust De-anonymization of Large Sparse Datasets (2008, methodology): “Some datasets include legally protected information such as health histories; others contain individual preferences and transactions, which many people may view as private or sensitive.”
Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning (2018, background): “Consequently, in the aforementioned instances, many identities of participating individuals were re-identiﬁed using a public voter database [75], IMDb movie ratings [57], and search keywords [8] respectively.”
Protecting Respondents' Identities in Microdata Release (2001, methodology): “Although this is not a trivial assumption, its enforcement is indeed possible and is today considered in many practical releases of data [17].”
How To Break Anonymity of the Netflix Prize Dataset (2006, methodology): “This has been demonstrated, for example, by Sweeney, who deanonymized medical records by joining them with a publicly available voter database [ 9 ], as well as by privacy breaches caused by publicly released AOL search data [5].”
Estimating the success of re-identifications in incomplete datasets using generative models (2019, methodology): “Yet, our analysis of the re-identi ﬁ cation of Gov. Weld by Latanya Sweeney shows that few attributes are often enough to render the likelihood of correct re-identi ﬁ cation very high.”
A firm foundation for private data analysis (2011, methodology): “In a notable demonstration of the power of auxiliary information, medical records of the governor of Massachusetts were identified by linking voter registration records to“anonymized” Massachusetts Group Insurance Commission (GIC) medical encounter data, which retained the birthdate, sex, and zip co”