Information Extraction Under Privacy Constraints

Asoodeh, Shahab; Díaz, Mario; Alajaji, Fady; Linder, Tamás

doi:10.3390/info7010015

Cited by 63 publications

(97 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other quantities from the information-theoretic literature have been used to quantify privacy and utility. For example, Asoodeh et al [14] and Calmon et al [16] used estimation-theoretic tools to characterize fundamental limits of privacy. Liao et al [37,38] explored the PUT within a hypothesis testing framework.…”

Section: Related Workmentioning

confidence: 99%

“…The feasibility of this goal depends on several factors including the chosen privacy and utility metric, as well as the topology and distribution of the data. The informationtheoretic approach to privacy, and notably the results by Sankar et al [10,11], Issa et al [12,13], Asoodeh et al [14,15], Calmon et al [16,17], among others, seek to quantify the best possible PUT for any privacy mechanism. In those works, information-theoretic quantities, such as mutual information and maximal leakage [12,13], have been used to characterize privacy, and bounds on the fundamental PUT were derived under assumptions on the distribution of the data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Privacy With Estimation Guarantees

Wang

Calmon

et al. 2019

IEEE Trans. Inform. Theory

View full text Add to dashboard Cite

We study the central problem in data privacy: how to share data with an analyst while providing both privacy and utility guarantees to the user that owns the data. In this setting, we present an estimation-theoretic analysis of the privacy-utility trade-off (PUT). Here, an analyst is allowed to reconstruct (in a mean-squared error sense) certain functions of the data (utility), while other private functions should not be reconstructed with distortion below a certain threshold (privacy). We demonstrate how χ 2 -information captures the fundamental PUT in this case and provide bounds for the best PUT. We propose a convex program to compute privacy-assuring mappings when the functions to be disclosed and hidden are known a priori and the data distribution is known. We derive lower bounds on the minimum mean-squared error of estimating a target function from the disclosed data and evaluate the robustness of our approach when an empirical distribution is used to compute the privacy-assuring mappings instead of the true data distribution. We illustrate the proposed approach through two numerical experiments.Index Terms-Estimation, privacy-utility trade-off, minimum mean-squared error.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Privacy With Estimation Guarantees

Wang

Calmon

et al. 2019

IEEE Trans. Inform. Theory

View full text Add to dashboard Cite

show abstract

“…Z|H (· | 1) − p Z|H (· | 0) T V ≤ 2I(H; Z) ≤ 2I(H; X | G • ) + ,and the lower bound in (8) follows from(28).We next prove the upper bound. Fix a subset of Γ ∈ Z s , and consider a p Z|X such thatp Z|X (z | x) = A, x ∈ I + , z ∈ Γ B, x ∈ I − , z ∈ Γ , p Z|X (z | x) = B, x ∈ I + , z ∈ Γ c A, x ∈ I − , z ∈ Γ cfor some A, B ≥ 0.…”

mentioning

confidence: 86%

Decentralized Detection With Robust Information Privacy Protection

Sun

Tay

2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

We consider a decentralized detection network whose aim is to infer a public hypothesis of interest. However, the raw sensor observations also allow the fusion center to infer private hypotheses that we wish to protect. We consider the case where there are an uncountable number of private hypotheses belonging to an uncertainty set, and develop local privacy mappings at every sensor so that the sanitized sensor information minimizes the Bayes error of detecting the public hypothesis at the fusion center, while achieving information privacy for all private hypotheses. We introduce the concept of a most favorable hypothesis (MFH) and show how to find a MFH in the set of private hypotheses. By protecting the information privacy of the MFH, information privacy for every other private hypothesis is also achieved. We provide an iterative algorithm to find the optimal local privacy mappings, and derive some theoretical properties of these privacy mappings. Simulation results demonstrate that our proposed approach allows the fusion center to infer the public hypothesis with low error while protecting information privacy of all the private hypotheses.

show abstract

“…This specific type of privacy-utility trade-off (PUT), and the optimal privacy mechanisms associated to it, has been investigated for several measures of privacy and utility, see, for example, [14,17,20,22]. These investigations often rely on the implicit assumption that the data distribution is, for the most part, known.…”

Section: Problem Setupmentioning

confidence: 99%

On the Robustness of Information-Theoretic Privacy Measures and Mechanisms

Díaz

Wang

Calmon

et al. 2020

IEEE Trans. Inform. Theory

Self Cite

View full text Add to dashboard Cite

Consider a data publishing setting for a dataset composed by both private and non-private features. The publisher uses an empirical distribution, estimated from n i.i.d. samples, to design a privacy mechanism which is applied to new fresh samples afterward. In this paper, we study the discrepancy between the privacy-utility guarantees for the empirical distribution, used to design the privacy mechanism, and those for the true distribution, experienced by the privacy mechanism in practice. We first show that, for any privacy mechanism, these discrepancies vanish at speed O(1/ √ n) with high probability. These bounds follow from our main technical results regarding the Lipschitz continuity of the considered information leakage measures. Then we prove that the optimal privacy mechanisms for the empirical distribution approach the corresponding mechanisms for the true distribution as the sample size n increases, thereby establishing the statistical consistency of the optimal privacy mechanisms. Finally, we introduce and study uniform privacy mechanisms which, by construction, provide privacy to all the distributions within a neighborhood of the estimated distribution and, thereby, guarantee privacy for the true distribution with high probability.

show abstract

Information Extraction Under Privacy Constraints

Cited by 63 publications

References 50 publications

Privacy With Estimation Guarantees

Privacy With Estimation Guarantees

Decentralized Detection With Robust Information Privacy Protection

On the Robustness of Information-Theoretic Privacy Measures and Mechanisms

Contact Info

Product

Resources

About