Differential Privacy: From Theory to Practice

Li, Ninghui; Lyu, Min; Su, Dong; Yang, Weining

doi:10.2200/s00735ed1v01y201609spt018

Cited by 106 publications

(85 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We computeâ −1 fromp and g n (1 ≤ n ≤ N ) by substituting (30), (31), and (32) into (28) (we can computeâ −1 with time complexity O(N K 2 ); for details, see Appendix B). It should be noted, however, thatQ in (32) may not be accurately computed, since the matrix λI K is added toŜ in (32). As a consequence,â −1 may also not be accurately computed.…”

Section: Proposed Algorithmmentioning

confidence: 99%

“…In fact, the bias of the proposed method was larger than that of the EM reconstruction method in our experiments (as shown in Appendix C). We consider this is because we applied the Tikhonov regularization to computeQ in (32). A regularization method is generally used to significantly reduce the variance by introducing a bias in the estimate.…”

Section: Optimization Of the Weight Parametermentioning

confidence: 99%

“…We denote the number of users who set = 0.1, 2, ln(K), and ∞ by N 1 , N 2 , N 3 , and N 4 , respectively (i.e., N = 4 i=1 N i ). We set = 0.1 and 2 in the high and middle privacy regime, respectively, since many studies used these values [24] and = 0.1 offers reasonably strong privacy protection [32]. We set = ln(K) in the low privacy regime, since a user sends different data (i.e., X n = Y n ) with probability 50% even in this case.…”

Section: Experimental Set-upmentioning

confidence: 99%

See 2 more Smart Citations

Toward Distribution Estimation under Local Differential Privacy with Small Samples

Murakami

Hino

Sakuma

2018

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

A number of studies have recently been made on discrete distribution estimation in the local model, in which users obfuscate their personal data (e.g., location, response in a survey) by themselves and a data collector estimates a distribution of the original personal data from the obfuscated data. Unlike the centralized model, in which a trusted database administrator can access all users’ personal data, the local model does not suffer from the risk of data leakage. A representative privacy metric in this model is LDP (Local Differential Privacy), which controls the amount of information leakage by a parameter ∈ called privacy budget. When ∈ is small, a large amount of noise is added to the personal data, and therefore users’ privacy is strongly protected. However, when the number of users ℕ is small (e.g., a small-scale enterprise may not be able to collect large samples) or when most users adopt a small value of ∈, the estimation of the distribution becomes a very challenging task. The goal of this paper is to accurately estimate the distribution in the cases explained above. To achieve this goal, we focus on the EM (Expectation-Maximization) reconstruction method, which is a state-of-the-art statistical inference method, and propose a method to correct its estimation error (i.e., difference between the estimate and the true value) using the theory of Rilstone et al. We prove that the proposed method reduces the MSE (Mean Square Error) under some assumptions.We also evaluate the proposed method using three largescale datasets, two of which contain location data while the other contains census data. The results show that the proposed method significantly outperforms the EM reconstruction method in all of the datasets when ℕ or ∈ is small.

show abstract

Section: Proposed Algorithmmentioning

confidence: 99%

Section: Optimization Of the Weight Parametermentioning

confidence: 99%

Section: Experimental Set-upmentioning

confidence: 99%

See 1 more Smart Citation

Toward Distribution Estimation under Local Differential Privacy with Small Samples

Murakami

Hino

Sakuma

2018

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

show abstract

“…In our scheme, the user rating datasets, D and D ′ are neighboring if D can be obtained from D ′ by adding or removing one element. Note that such a definition is usually adopted in Unbounded DP [17]. In this paper, however, we mainly denote datasets by matrices with setting all unselected (and blank) ratings to zero.…”

Section: Differential Privacymentioning

confidence: 99%

Probabilistic matrix factorization with personalized differential privacy

Zhang

Liu

Chen

et al. 2019

Knowledge-Based Systems

View full text Add to dashboard Cite

Probabilistic matrix factorization (PMF) plays a crucial role in recommendation systems. It requires a large amount of user data (such as user shopping records and movie ratings) to predict personal preferences, and thereby provides users high-quality recommendation services, which expose the risk of leakage of user privacy. Differential privacy, as a provable privacy protection framework, has been applied widely to recommendation systems. It is common that different individuals have different levels of privacy requirements on items. However, traditional differential privacy can only provide a uniform level of privacy protection for all users.In this paper, we mainly propose a probabilistic matrix factorization recommendation scheme with personalized differential privacy (PDP-PMF). It aims to meet users' privacy requirements specified at the item-level instead of giving the same level of privacy guarantees for all. We then develop a modified sampling mechanism (with bounded differential privacy) for achieving PDP. We also perform a theoretical analysis of the PDP-PMF scheme and demonstrate the privacy of the PDP-PMF scheme. In addition, we implement the probabilistic matrix factorization schemes both with traditional and with personalized differential privacy (DP-PMF, PDP-PMF) and compare them through a series of experiments. The results show that the PDP-PMF scheme performs well on protecting the privacy of each user and its recommendation quality is much better than the DP-PMF scheme.

show abstract

“…Lemma 2 (Convexity [28]). Given k mechanisms M 1 , M 2 , ..., M k that satisfy -differential privacy, and p 1 , p 2 , ..., p k ∈ [0,1] such that k i=1 p i = 1, let M denote the mechanism that applies M i with probability p i .…”

Section: B Related Solution Conceptsmentioning

confidence: 99%

Differentially Private Double Spectrum Auction With Approximate Social Welfare Maximization

Chen

Zhong

et al. 2019

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Spectrum auction is an effective approach to improving spectrum utilization, by leasing idle spectrum from primary users to secondary users. Recently, a few differentially private spectrum auction mechanisms have been proposed, but, as far as we know, none of them addressed the differential privacy in the setting of double spectrum auctions. In this paper, we combine the concept of differential privacy with double spectrum auction design, and present a Differentially private Double spectrum auction mechanism with approximate Social welfare Maximization (DDSM). Specifically, we design the mechanism by employing the exponential mechanism to select clearing prices for the double spectrum auction with probabilities exponentially proportional to the related social welfare values, and then improve the mechanism in several aspects like the designs of the auction algorithm, the utility function and the buyer grouping algorithm. Through theoretical analysis, we prove that DDSM achieves differential privacy, approximate truthfulness, approximate social welfare maximization. Extensive experimental evaluations show that DDSM achieves a good performance in term of social welfare.

show abstract

Differential Privacy: From Theory to Practice

Cited by 106 publications

References 79 publications

Toward Distribution Estimation under Local Differential Privacy with Small Samples

Toward Distribution Estimation under Local Differential Privacy with Small Samples

Probabilistic matrix factorization with personalized differential privacy

Differentially Private Double Spectrum Auction With Approximate Social Welfare Maximization

Contact Info

Product

Resources

About