Data privacy through optimal k-anonymization

By Roberto J. Bayardo Jr., Rakesh Agrawal. IEEE International Conference on Data Engineering, 2005

1,404 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Science Applications

View Paper: https://www.semanticscholar.org/paper/d429d387f94e16fe2fcf63224758df9b0ff81430

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 Computer Science Applications

Citations in the corpus

M-invariance: towards privacy preserving re-publication of dynamic datasets (2007, methodology): “In that case, the optimal relation can b e found efficiently by using several heuristics [5, 12] to prune the s earch space.”
δ-Presence without Complete World Knowledge (2010, methodology): “utility of the data set), as determined by the Loss Metric (LM) [18] and the Discernibility Metric [ 19 ].”
Privacy: Theory meets Practice on the Map (2008, background): “These algorithms include generalizations [23], [24], [25], cell and tuple suppression [26], [25], random perturbation [22], [27], publishing marginals that satisfy a safety range [28], and data swapping [29] (where attributes”
Fast Data Anonymization with Low Information Loss (2007, methodology): “[3] proposes an optimal algorithm for single-dimensional recoding with respect to the CM and DM metrics.”
k -Anonymous Data Mining: A Survey (2008, methodology): “been married M [40-100) 17 been married F [1-40) 2 been married F [40-100) 9 never married M [40-100) 26”
A Survey of Quantification of Privacy Preserving Data Mining Algorithms (2008, background): “In [2], Agrawal and Srikant uses an additive-noise-based technique to perturb data.”
Differentially private data release for data mining (2011, methodology): “Bayardo and Agrawal [2] also address the classi.cation problem using the same classi.cation metric of [18].”
L-diversity: privacy beyond k-anonymity (2006, neutral): “Because of its conceptual simplicity, k-anonymity has been widely discussed as a viable definition of privacy in data publishing, and due to algorithmic advances in creating k-anonymous versions of a dataset [3] [6] [16] [18] [21] [24] [25], k-anonymity has grown in popularity.”
Anatomy: simple and effective privacy preservation (2006, background): “As another direction, it would be highly useful to study how anatomized tables can be utilized for effective mining of interesting patterns in the microdata, perhaps through minimization of other metrics of measuring information loss (e.g., KL-divergence [7] and discernibility [4, 9]).”
Hiding the presence of individuals from shared databases (2007, methodology): “We evaluate how varying δ affects the cost of anonymizing the dataset, as determined by the Loss Metric (LM) [9] and the Discernibility Metric (DM) [5].”
Worst-Case Background Knowledge for Privacy-Preserving Data Publishing (2007, background): “The monotonicity property allows us to make use of existing algorithms for efficient itemset mining [4], k-anonymity [7, 22] andl-diversity [24].”
On the tradeoff between privacy and utility in data publishing (2009, background): “choosing k = 10 in k-anonymity), how to generate an anonymized dataset that maximizes a particular utility measure, which can be the number of equivalence class [21], or the discernibility metric [4].”
PrivBayes: private data release via bayesian networks (2014, background): “In particular, the results suggest an appropriate value should be within [3, 6].”