Random projection-based multiplicative data perturbation for privacy preserving distributed data mining

By Kun Liu, Hillol Kargupta, Jessica Ryan. IEEE Transactions on Knowledge and Data Engineering, 2006

631 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Statistics and Probability, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ba818e6955a4f0e031d71f8a234daa1049d3d9ce

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Statistics and Probability

In Signal Processing

Citations in the corpus

Compressed Regression (2007, background): “The work of [12] is closely related to our work at a high level, in t ha it considers low rank random linear transformations of either the row space or column space of th e dataX.”
Differential privacy with compression (2009, methodology): “The work of [15] and [23], like the work presented here, both consider low rank random linear transformations of the data X , and discuss privacy and utility.”
Secure and Privacy-Preserving Consensus (2017, background): “Definition 1 requires that an honest-but-curious adversary cannot even find a range for a private value and thus is more stringent than the privacy preservation definition considered in [34]–[36], which defines privacy preservation as the inability of an adversary to uniquely determine the protected”
The applicability of the perturbation based privacy preserving data mining for real-world data (2008, background): “Some other researchers have proposed different noise addition techniques to protect the private data [7] [8] [9].”
Disease Diagnosis in Smart Healthcare: Innovation, Technologies and Applications (2017, methodology): “Common privacy-preserving methods include disclosure control [162,163], output perturbation [164,165] and anonymization [166,167].”
Very sparse random projections (2006, methodology): “[31] Kun Liu, Hillol Kargupta, and Jessica Ryan.”
A General Survey of Privacy-Preserving Data Mining Models and Algorithms (2008, background): “This is especially true of outlier records which can be easily distinguished from other records in their locality.”
Compressed and Privacy-Sensitive Sparse Regression (2009, background): “The work in [24] is closely related to the current paper at a high level, in that it considers low-rank random linear transformations of either the row space or column space of the data .”
Secret Sharing vs . Encryption-based Techniques For Privacy Preserving Data Mining 1 (2008, methodology): “lected according to the same probability distribution as the original data set[15, 16].”
Secret charing vs. encryption-based techniques for privacy preserving data mining (2007, methodology): “lected according to the same probability distribution as the original data set[16, 17].”
Compressive mechanism: utilizing sparse representation in differential privacy (2011, neutral): “[48, 47, 32] apply random projections to differential privacy.”
Privacy via the Johnson-Lindenstrauss Transform (2012, methodology): “Liu et al. [22] introduce and motivate the problem of releasing data to third parties with a goal that the original sensitive information cannot be inferred while preserving analytic properties of the data, such as inner product and Euclidean distance computations.”
Distributed Clustering in the Anonymized Space with Local Differential Privacy (2019, background): “The additive data perturbation (ADP [24]) and the random subspace projection (RSP [25]) are two of the most common approaches to transfer original data to the anonymized space in the literature.”
Near-optimal Differentially Private Principal Components (2012, neutral): “Algorithm PPCA is ↵-differentially private.”
Near-Optimal Algorithms for Differentially-Private Principal Components (2012, methodology): “ving singular value decomposition in this model [Han et al., 2009]. Finally, dimension reduction through random projection has been considered as a technique for sanitizing data prior to publication [Liu et al., 2006]; our work diers from this line of work in that we oer dierential privacy guarantee”