A Practical Differentially Private Random Decision Tree Classifier

By Geetha Jagannathan, Krishnan Pillaipakkamnatt, Rebecca N. Wright. 2009

221 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

Stealing Machine Learning Models via Prediction APIs (2016, methodology): “DP learning has been applied to regressions [17,56], SVMs [44], decision trees [31] and neural networks [48].”
Understanding Membership Inferences on Well-Generalized Learning Models (2018, methodology): “It has been applied to various machine learning models including decision trees [19], logistic regression [41], and neural networks [4,31].”
A Semi-Supervised Learning Approach to Differential Privacy (2013, methodology): “In this section, we present our experimental results that show that non-private data can be used to improve the utility of the differentially private random decision tree classifier [13], especially when the size of the private data set is relatively small.”
No free lunch in data privacy (2011, methodology): “First, we use a no-free-lunch theorem, which de.nes nonprivacy as a game, to argue that it is not possible to provide privacy and utility without making assumptions about how the data are generated.”
Privately releasing conjunctions and the statistical query barrier (2010, methodology): “We then take advantage of Vondrak’s observation in [Von10] that Lipschitz submodular functions are self-bounding , which allows us to apply recent dimension-free concentration bounds for self-bounding functions [BLM00, BLM09].”
Privacy-preserving Transfer Learning for Knowledge Sharing (2018, background): “…the performance of machine learning, including logistic regression (Chaudhuri, Monteleoni, and Sarwate 2011), tree models (Emekc¸i et al. 2007; Jagannathan, Pillaipakkamnatt, and Wright 2009; Fong and Weber-Jahnke 2012), and deep neural networks (Shokri and Shmatikov 2015; Abadi et al. 2016),…”
Towards Measuring Membership Privacy (2017, background): “Previous work has shown that a large amount of noise is needed to make ID3 differentially private while it is more practical to achieve differential privacy for a random decision tree [18].”
Differential Privacy and Machine Learning: a Survey and Review (2014, unknown): “[24] proposes an ǫ-differentially private mechanism.”
Large Margin Gaussian Mixture Models with Differential Privacy (2012, background): “Jagannathan et al. [11] present a differentially private random decision tree learning algorithm which can be applied to multiclass classification.”
Differential Privacy in Telco Big Data Platform (2015, background): “…on DP from industrial perspectives: • Implementation in telco big data platform: We broadly categorize the recent DP implementations for DTs into three basic architectures: 1) Data Publication Architecture [25, 39]; 2) Separated Architecture [7]; and 3) Hybridized Architecture [7, 13].”
Privacy Preserving Synthetic Data Release Using Deep Learning (2018, background): “Differential privacy has been implemented in a number of data analysis tasks, including regression models [7, 37], classification models [17, 26, 31] and association rule mining [20, 35].”
Differentially Private Data Publishing and Analysis: A Survey (2017, methodology): “[55] provided an algorithm for building random private decision trees, which randomly select attributes to create nodes.”