Data mining with differential privacy

By Arik Friedman, Assaf Schuster. 2010

524 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Sociology and Political Science

Citations in the corpus

A Hybrid Approach to Privacy-Preserving Federated Learning (2018, methodology): “budget, we follow the approach from [19] to divide the budget for each iteration and set a fixed number of iterations rather than a purity test as a stopping condition.”
Functional Mechanism: Regression Analysis under Differential Privacy (2012, methodology): “For instance, the exponential mechanism has been applied for the publication of audition results [21], coresets [10], frequent patterns [3], decision trees [11], support vector machines [25], and synthetic datasets [7,16].”
Distributed Data Mining with Differential Privacy (2011, background): “A sequence of query with i-differential privacy provides ∑ i idifferential privacy [15], [19].”
Discrimination- and privacy-aware patterns (2015, methodology): “In Friedman and Schuster (2010), an algorithm is proposed for building a classifier while guaranteeing differential privacy.”
Differentially Private K-Means Clustering (2015, background): “Friedman and Schuster [13] made the ID3 decision tree construction algorithm differentially private.”
Differentially Private Algorithms for Empirical Machine Learning (2014, methodology): “ed by adding or removing one tuple. The sensitivity of the total score TC, difference score DC, and purity index PIare all 1. The sensitivity of information gain function has been shown to be O(logn) [9, 29], where nis (an upper bound on) the number of tuples in the dataset. Information gain is cons”
Privacy-Preserving Distributed Multi-Task Learning with Asynchronous Updates (2017, methodology): “Friedman and Schus-ter [22] used a data mining approach that demonstrates the trade off between privacy, accuracy, and the sample size, and Li et al. [33] optimized linear counting queries.”
Differentially private data release for data mining (2011, methodology): “Does the interactive approach offer better data mining results than the noninteractive approach? Does differentially private data provide less utility than k-anonymous data? Experimental results demonstrate that our algorithm outperforms the recently proposed differentially-private interactive algor”
The Large Margin Mechanism for Differentially Private Maximization (2014, background): “There has been a large amount of work on differential privacy for a wide range of statistical and machine learning tasks over the last decade [6, 30, 13, 21, 33, 24, 1]; for overviews, see [18] and [29].”
Differentially Private Deep Learning with Smooth Sensitivity (2020, background): “To satisfy the increasing demand for preserving privacy, differential privacy (DP) [12] was proposed as a rigorous principle that guarantees provable privacy protection and has been extensively applied [4, 17, 35].”
Differentially private histogram publication (2012, unknown): “[15] devise methods for constructing decision trees.”
Convergence Rates for Differentially Private Statistical Estimation (2012, background): “In diﬀerentially private solutions, privacy is guaranteed by ensuring that the participation of a single individual in a database does not change the outcome of a private algorithm by much.”
A Practical Differentially Private Random Decision Tree Classifier (2009, background): “There has been a substantial amount of work on differentially private classifiers, including differentially private ID3 [17] (discussed in more detail below).”
PrivBasis: Frequent Itemset Mining with Differential Privacy (2012, background): “More recently, differential privacy has been adapted to release accurate data mining models and results [19, 29, 8].”
Evaluating Differentially Private Machine Learning in Practice (2019, background): “Some of the early data analytics works on frequent pattern mining [7,41], decision trees [21], private record linkage [30] and recommender systems [48] were able to achieve both high utility and privacy with settings close to 1.”
Personal privacy vs population privacy: learning to attack anonymization (2011, background): “Indeed, there has been much prior work discussing the suitability of differential privacy for accurate learning [18, 12, 8].”