Differential privacy in new settings

By Cynthia Dwork. 2010

181 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

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 Computational Theory and Mathematics

Citations in the corpus

Collecting Telemetry Data Privately (2017, background): “ databases to trade-off privacy for utility. On a different but relevant line of work about streaming model of DP [14], the event-level private counting problem under continual observation is studied [11], with almost tight upper bounds in error (polynomial in logT) in [13] and [7]. [24] proposes a ”
Location Privacy Protection Based on Differential Privacy Strategy for Big Data in Industrial Internet of Things (2018, background): “As attackers grasp more background knowledge, these methods cannot effectively protect the user’s location data privacy, and the lack of privacy protection about the type of relational privacy protection method is proposed in [18].”
Generating synthetic data in finance: opportunities, challenges and pitfalls (2020, methodology): “Publishing stream data with privacy guarantees was ﬁrst addressed by Dwork [35] and Dwork et al. [36].”
Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT (2020, background): “Differential privacy [4] provides the most reliable privacy guarantee, which is generally considered strong enough to protect data from privacy attacks.”
Differentially Private Asynchronous Federated Learning for Mobile Edge Computing in Urban Informatics (2020, background): “Unlike the conventional differential privacy [18] which provides guarantee in data analysis phase, LDP focuses on the privacy in data collection process towards data collectors.”
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy (2023, methodology): “Definition 2 ((ε, δ)-Differential Privacy, Dwork et al. (2006a)).”
A Practical Differentially Private Random Decision Tree Classifier (2009, background): “Differential privacy has attracted a substantial amount of attention and further research (much of which is surveyed in [8, 9, 10, 11]).”
Differentially Private Data Publishing and Analysis: A Survey (2017, background): “’s report [5] exploited the difficulties that arise when data publishing encounters prospective solutions in the context of statistics analysis.”
Differentially Private Event Sequences over Infinite Streams (2014, background): “The works that aim at event-level privacy in inﬁnite streams [11, 27, 6, 7] capture counter-based scenarios, whereas in our model each event contributes to a single published statistic.”
Impossibility of Differentially Private Universally Optimal Mechanisms (2010, background): “These and other techniques allow performing a wide scope of analyses in a differentially private manner such as conducting surveys over sensitive information, computing statistics, data mining, and sanitization/data release (see the surveys in [2, 3]).”
Private and Continual Release of Statistics (2010, methodology): “used the notion of pan privacy in the continual counter mechanism [6, 9], and showed how to make their counter mechanism resilient against a single unannounced intrusion.”
Differentially Private Online Learning (2011, unknown): “Over the years, the privacy community have developed differentially private algorithms for several interesting problems [6, 7, 8].”