A Condensation Approach to Privacy Preserving Data Mining

By Charu C. Aggarwal, Philip S. Yu. 2004

436 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Science Applications, Sociology and Political Science

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

In Sociology and Political Science

Citations in the corpus

Data Synthesis based on Generative Adversarial Networks (2018, methodology): “Other baseline methods to generate synthetic records are the condensation method [8] and DCGAN.”
Privacy-preserving SVM classification (2008, positive): “Recently, some alternative techniques such as condensation [2] and transformation [27] have also been proposed, though the security properties of these need to be carefully investigated.”
Privacy preserving data classification with rotation perturbation (2005, methodology): “However, the two metrics are not well-balanced in many existing perturbation techniques [3] [2] [5] [1].”
Privacy-Preserving SVM Classification on Vertically Partitioned Data (2006, methodology): “Recently, some alternative techniques such as condensation[13] and transformation [14] have also been proposed.”
Secret Sharing vs . Encryption-based Techniques For Privacy Preserving Data Mining 1 (2008, background): “In [2], the authors propose an approach for privacy preserving data mining which maps the original data set into a new anonymized data set preserving the correlations among the different dimensions.”
L-diversity: privacy beyond k-anonymity (2006, neutral): “[ 1-10 ], [11-20], etc), we would end up with very large q ∗ -blocks.”
A General Survey of Privacy-Preserving Data Mining Models and Algorithms (2008, methodology): “In [8], a related method has been independently proposed for condensation based privacy-preserving data mining.”
Towards trajectory anonymization: a generalization-based approach (2008, methodology): “) One proposed technique to solve this issue is reconstruction [38, 1] where an atomic dataset is recreated from the anonymized dataset by uniformly selecting atomic points from anonymized regions.”
L-diversity: Privacy beyond k-anonymity (2007, positive): “There has been a lot of study into creating efficient algorithms for k-anonymity using generalization and tuple suppression techniques [2, 6, 16, 22].”
Efficient k -Anonymization Using Clustering Techniques (2007, methodology): “In the hierarchy-based generalization, the quality and usefulness of results depends heavily on the choice of the generalization hierarchy, which relies on the user’s knowledge of the specific domain [ 2 ].”
A Survey of Inference Control Methods for Privacy-Preserving Data Mining (2008, methodology): “A similar idea called data condensation had also been independently proposed by [4] to achieve k-anonymity for the specific case of numerical attributes.”
Discovering frequent patterns in sensitive data (2010, background): “While there is extensive work on privacy breach when the complete data set is published [25, 3, 7], studying privacy breach when only certain statistics about data are revealed is relatively new [11, 10].”
A Survey of Multiplicative Perturbation for Privacy-Preserving Data Mining (2008, methodology): “Only recently, the data management community has shown some development on multi-dimensional data perturbation techniques, such as the condensation approach using k-nearest neighbor (kNN) method [1], the multi-dimensional K-anonymization using kd-tree [24], and the multiplicative data perturbation t”
Secret charing vs. encryption-based techniques for privacy preserving data mining (2007, neutral): “In [2], the”
Never Walk Alone: Uncertainty for Anonymity in Moving Objects Databases (2008, methodology): “Given a dataset of trajectories D and a time interval T , we denote: DT = {τ ∈ D|τ is defined exactly in T}.”