Our data, ourselves: privacy via distributed noise generation
Cynthia Dwork,Krishnaram Kenthapadi,Frank McSherry,Ilya Mironov,Moni Naor +4 more
- Vol. 4004, pp 486-503
TLDR
In this paper, a distributed protocol for generating shares of random noise, secure against malicious participants, was proposed, where the purpose of the noise generation is to create a distributed implementation of the privacy-preserving statistical databases described in recent papers.Abstract:
In this work we provide efficient distributed protocols for generating shares of random noise, secure against malicious participants. The purpose of the noise generation is to create a distributed implementation of the privacy-preserving statistical databases described in recent papers [14,4,13]. In these databases, privacy is obtained by perturbing the true answer to a database query by the addition of a small amount of Gaussian or exponentially distributed random noise. The computational power of even a simple form of these databases, when the query is just of the form ∑if(di), that is, the sum over all rows i in the database of a function f applied to the data in row i, has been demonstrated in [4]. A distributed implementation eliminates the need for a trusted database administrator.
The results for noise generation are of independent interest. The generation of Gaussian noise introduces a technique for distributing shares of many unbiased coins with fewer executions of verifiable secret sharing than would be needed using previous approaches (reduced by a factor of n). The generation of exponentially distributed noise uses two shallow circuits: one for generating many arbitrarily but identically biased coins at an amortized cost of two unbiased random bits apiece, independent of the bias, and the other to combine bits of appropriate biases to obtain an exponential distribution.read more
Citations
More filters
Proceedings ArticleDOI
The structure of optimal private tests for simple hypotheses
TL;DR: In this article, the Neyman-Pearson lemma is used to characterize the sample complexity of private hypothesis testing, up to constant factors in terms of the structure of P and Q and the privacy level e, and show that this sample complexity is achieved by a certain randomized and clamped variant of the log-likelihood ratio test.
Proceedings ArticleDOI
The Privacy of the Analyst and the Power of the State
TL;DR: It is argued that the problem is real by proving an exponential gap between the number of queries that can be answered (with non-trivial error) by stateless and stateful differentially private mechanisms.
Journal ArticleDOI
Federated learning and differential privacy for medical image analysis
TL;DR: In this article , a case study of applying a differentially private federated learning framework for analysis of histopathology images, the largest and perhaps most complex medical images, was conducted.
Posted Content
Shredder: Learning Noise Distributions to Protect Inference Privacy
Fatemehsadat Mireshghallah,Mohammadkazem Taram,Ramrakhyani Prakash S,Dean M. Tullsen,Hadi Esmaeilzadeh +4 more
TL;DR: Shredder is an end-to-end framework that, without altering the topology or the weights of a pre-trained network, learns additive noise distributions that significantly reduce the information content of communicated data while maintaining the inference accuracy.
Posted Content
On-Average KL-Privacy and its equivalence to Generalization for Max-Entropy Mechanisms
TL;DR: On-Average KL-Privacy as mentioned in this paper is a generalization of differential privacy that is equivalent to generalization for Gibbs distributions, a class of distributions that arises naturally from the maximum entropy principle.
References
More filters
Book ChapterDOI
Calibrating noise to sensitivity in private data analysis
TL;DR: In this article, the authors show that for several particular applications substantially less noise is needed than was previously understood to be the case, and also show the separation results showing the increased value of interactive sanitization mechanisms over non-interactive.
Journal ArticleDOI
The Byzantine Generals Problem
TL;DR: The Albanian Generals Problem as mentioned in this paper is a generalization of Dijkstra's dining philosophers problem, where two generals have to come to a common agreement on whether to attack or retreat, but can communicate only by sending messengers who might never arrive.
Book ChapterDOI
The Byzantine generals problem
TL;DR: In this article, a group of generals of the Byzantine army camped with their troops around an enemy city are shown to agree upon a common battle plan using only oral messages, if and only if more than two-thirds of the generals are loyal; so a single traitor can confound two loyal generals.
Journal Article
Calibrating noise to sensitivity in private data analysis
TL;DR: The study is extended to general functions f, proving that privacy can be preserved by calibrating the standard deviation of the noise according to the sensitivity of the function f, which is the amount that any single argument to f can change its output.
Proceedings ArticleDOI
How to play ANY mental game
TL;DR: This work presents a polynomial-time algorithm that, given as a input the description of a game with incomplete information and any number of players, produces a protocol for playing the game that leaks no partial information, provided the majority of the players is honest.