On privacy-utility tradeoffs for constrained data release mechanisms

Basciftci, Y. Ozan; Wang, Ye; Ishwar, Prakash

doi:10.1109/ita.2016.7888175

Cited by 58 publications

(35 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The highest privacy standard that a data disclosure strategy can guarantee, called perfect privacy, corresponds to when nothing can be learned about an individual that could not have been learned without the disclosed data anyway [4]. While studied in [5], [6], perfect privacy is often disregarded for being too restrictive, corresponding to a extreme choice within the trade-off that exists between privacy and utility [7], [8]. The most popular approach that takes advantage of this trade-off is differential privacy [9], which is equipped with free parameters that can be flexibly tuned in order to adapt to the requirements of diverse scenarios.…”

Section: Arxiv:190401711v1 [Csit] 2 Apr 2019mentioning

confidence: 99%

“…Another related problem to the one considered here is the privacy funnel, in which the goal is to reveal the data set X within a given accuracy under some utility measure, while keeping the latent variable W as private as possible [18]. Also, various metrics for quantifying the quality of the disclosure strategy has been studied in [6], [8], [19], [20].…”

Section: B Scenario and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Data Disclosure Under Perfect Sample Privacy

Rassouli

Rosas

Gündüz

2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Perfect data privacy seems to be in fundamental opposition to the economical and scientific opportunities associated with extensive data exchange. Defying this intuition, this paper develops a framework that allows the disclosure of collective properties of datasets without compromising the privacy of individual data samples. We present an algorithm to build an optimal disclosure strategy/mapping, and discuss it fundamental limits on finite and asymptotically large datasets. Furthermore, we present explicit expressions to the asymptotic performance of this scheme in some scenarios, and study cases where our approach attains maximal efficiency. We finally discuss suboptimal schemes to provide sample privacy guarantees to large datasets with a reduced computational cost.

show abstract

Section: Arxiv:190401711v1 [Csit] 2 Apr 2019mentioning

confidence: 99%

Section: B Scenario and Related Workmentioning

confidence: 99%

Data Disclosure Under Perfect Sample Privacy

Rassouli

Rosas

Gündüz

2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…The authors in [10] used the notion of self-information cost to design optimal randomized privacy filters for improving the privacy of a (private) random variable correlated with a public random variable. The interested reader is referred to [11], [12], [13] and references therein for a detailed investigation of the information theoretic approaches to data privacy problem.…”

Section: Related Workmentioning

confidence: 99%

Privacy of Information Sharing Schemes in a Cloud-based Multi-sensor Estimation Problem

Nekouei

Skoglund

Johansson

2018

2018 Annual American Control Conference (ACC)

View full text Add to dashboard Cite

In this paper, we consider a multi-sensor estimation problem wherein each sensor collects noisy information about its local process, which is only observed by that sensor, and a common process, which is simultaneously observed by all sensors. The objective is to assess the privacy level of (the local process of) each sensor while the common process is estimated using cloud computing technology. The privacy level of a sensor is defined as the conditional entropy of its local process given the shared information with the cloud. Two information sharing schemes are considered: a local scheme, and a global scheme. Under the local scheme, each sensor estimates the common process based on its the measurement and transmits its estimate to a cloud. Under the global scheme, the cloud receives the sum of sensors' measurements. It is shown that, in the local scheme, the privacy level of each sensor is always above a certain level which is characterized using Shannon's mutual information. It is also proved that this result becomes tight as the number of sensors increases. We also show that the global scheme is asymptotically private, i.e., the privacy loss of the global scheme decreases to zero at the rate of O (1/M ) where M is the number of sensors.

show abstract

“…A wide variety of methods to statistically quantify and address privacy have been proposed, such as k-anonymity [30], L-diversity [18], t-closeness [16], and differential privacy [5]. In our work, we focus on an information-theoretic approach where privacy is quantified by the mutual information between the data release and the sensitive information [35], [27], [3], [28], [2].…”

Section: Introductionmentioning

confidence: 99%

“…We build upon the non-asymptotic, information-theoretic framework introduced by [27], [3], where the sensitive and useful data are respectively modeled as random variables X and Y . We also adopt the extension considered in [2], where only a (potentially partial and/or noisy) observation W of the data is available. In this framework, the design of the privacy-preserving mechanism to release Z is formulated as the optimization of the tradeoff between minimizing privacy-leakage quantified by the mutual information I(X; Z) and minimizing an expected distortion E[d(Y, Z)].…”

Section: Introductionmentioning

confidence: 99%

Privacy-Preserving Adversarial Networks

Tripathy

Wang

Ishwar

2019

2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)

Self Cite

View full text Add to dashboard Cite

We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive information. Our approach employs adversarially-trained neural networks to implement randomized mechanisms and to perform a variational approximation of mutual information privacy. We validate our Privacy-Preserving Adversarial Networks (PPAN) framework via proof-of-concept experiments on discrete and continuous synthetic data, as well as the MNIST handwritten digits dataset. For synthetic data, our model-agnostic PPAN approach achieves tradeoff points very close to the optimal tradeoffs that are analytically-derived from model knowledge.In experiments with the MNIST data, we visually demonstrate a learned tradeoff between minimizing the pixel-level distortion versus concealing the written digit.

show abstract

On privacy-utility tradeoffs for constrained data release mechanisms

Cited by 58 publications

References 11 publications

Data Disclosure Under Perfect Sample Privacy

Data Disclosure Under Perfect Sample Privacy

Privacy of Information Sharing Schemes in a Cloud-based Multi-sensor Estimation Problem

Privacy-Preserving Adversarial Networks

Contact Info

Product

Resources

About