Tools for privacy preserving distributed data mining

By Chris Clifton, Murat Kantarcioglu, Jaideep Vaidya, Xiaodong Lin, Michael Y. Zhu. 2002

1,051 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Privacy & Security

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 Privacy & Security

Citations in the corpus

Secure Federated Submodel Learning (2019, background): “In the data mining field, the representative design of private set union [86] is based on commutative encryption and requires direct communication between any pair of two parties.”
A Comprehensive Comparison of Multiparty Secure Additions with Differential Privacy (2015, methodology): “Among all secure computation schemes, we evaluate three representative groups: secret sharing [9], [49], homomorphic encryption [2], [33], [44], [50], and perturbationbased [16].”
Privacy Preserving Data Mining (2015, methodology): “It also defines Secure Sum, Secure Set Intersection and Secure set Union techniques [3].”
Privacy-Preserving Multivariate Statistical Analysis: Linear Regression and Classification (2004, background): “Another general approach is the secure multi-party computation approach [ 7 ,12,18,21,25].”
Privacy Preserving Naïve Bayes Classifier for Vertically Partitioned Data (2004, background): “Details and references to more work can be found at [3].”
L-diversity: privacy beyond k-anonymity (2006, neutral): “Clifton et al. [ Clifton et al. 2002 ] describes methods to implement basic operations like secure sum, secure set union, secure set intersection, and secure scalar product using both encryption and additive randomization in the secure multiparty computation setting.”
Secure multiparty aggregation with differential privacy: a comparative study (2013, methodology): “Among them are: a secure sum protocol, a secure union protocol, and a secure scalar product [11].”
Distributed Sparse Linear Regression (2010, background): “In other cases, such as the Internet or collaborative interlaboratory studies, agents providing private data for the purpose of ﬁtting, e.g., a sparse model, may not be willing to share their training data but only the learning results [8], [12].”
New Efficient Attacks on Statistical Disclosure Control Mechanisms (2008, background): “There is a a vast body of work on this subject (for references, see [1, 6, 10, 24, 25, 26]).”
Secure MPC for Analytics as a Web Application (2016, positive): “Appendix The protocol developed for this application is a variant of a technique that allows multiple parties to securely compute a sum of their private inputs [13], though the naïve secure sum protocol could not be deployed as-is: • participants must pass data along in sequence, requiring a sophist”
Privacy-Preserving Machine Learning Algorithms for Big Data Systems (2015, methodology): “Randomization-based approaches protect the private data by adding noise to the original data.”
Privacy preserving regression modelling via distributed computation (2004, background): “tion protocol [1, 3 ] can be used to effect this computation.”
Privacy-preserving data mining: why, how, and when (2004, methodology): “Other recent methods include naïve Bayes classification, an ID3 classifier for vertically partitioned data, and clustering on both vertically and horizontally partitioned data.(13)”
Privacy-preserving data publishing: A survey of recent developments (2010, methodology): “We refer readers interested in PPDDM to work by [Clifton et al. 2002; Kantarcioglu 2008; Pinkas 2002; Vaidya 2008; Wright et al. 2005].”
A taxonomy of privacy-preserving record linkage techniques (2013, methodology): “(ii) Secure multi-party computation ( SMC ): The basic idea of SMC is that a computation is secure if at the end of the computation no party knows anything except its own input and the ﬁnal results of the computed function [82,83,93].”