Connecting Robust Shuffle Privacy and Pan-Privacy

Balcer, Victor; Cheu, Albert; Joseph, Matthew; Mao, Jieming

doi:10.1137/1.9781611976465.142

Cited by 25 publications

(67 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the DP literature, the Element Distinctness problem has been well-studied, see, e.g., [7,18,20,25,49,53]. Moreover, estimating the frequency histogram is related to the anonymized histogram problem [43,57].…”

Section: Related Work and Alternativesmentioning

confidence: 99%

“…Our protocol, specifically the SampleNoise procedure (Algorithm 4), will select the following parameters: µ υ = 65, µ η = 132, µ κ = 459, µ λ = 680, µ χ = 699. Plugging this back into (7) implies that the expected total number of noise registers added is ≤ 18K, which is an acceptable overhead for, e.g., sketch size m = 100K. Note that the number of noise registers can be reduced further by allocating more privacy budget to χ , κ , λ , but will result in worse accuracy (as indicated by ( 9), ( 8)).…”

Section: Privacy Guaranteementioning

confidence: 99%

See 1 more Smart Citation

Multiparty Reach and Frequency Histogram: Private, Secure, and Practical

Ghazi

Kreuter

Kumar

et al. 2021

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

Consider the setting where multiple parties each hold a multiset of users and the task is to estimate the reach (i.e., the number of distinct users appearing across all parties) and the frequency histogram (i.e., fraction of users appearing a given number of times across all parties). In this work we introduce a new sketch for this task, based on an exponentially distributed counting Bloom filter. We combine this sketch with a communication-efficient multi-party protocol to solve the task in the multi-worker setting. Our protocol exhibits both differential privacy and security guarantees in the honest-but-curious model and in the presence of large subsets of colluding workers; furthermore, its reach and frequency histogram estimates have a provably small error. Finally, we show the practicality of the protocol by evaluating it on internet-scale audiences.

show abstract

Section: Related Work and Alternativesmentioning

confidence: 99%

Section: Privacy Guaranteementioning

confidence: 99%

Multiparty Reach and Frequency Histogram: Private, Secure, and Practical

Ghazi

Kreuter

Kumar

et al. 2021

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

show abstract

“…Recent research on the shuffle DP model includes work on aggregation (Balle et al, 2019;Ghazi et al, 2020d;Balle et al, 2020), histograms and heavy hitters (Ghazi et al, 2021;Balcer and Cheu, 2020;Ghazi et al, 2020a,c), and counting distinct elements (Balcer et al, 2021;Chen et al, 2021).…”

Section: A Proofs Of Lemma 8 and Lemmamentioning

confidence: 99%

Locally Private k-Means in One Round

Chang¹,

Ghazi²,

Kumar³

et al. 2021

Preprint

View full text Add to dashboard Cite

We provide an approximation algorithm for k-means clustering in the one-round (aka non-interactive) local model of differential privacy (DP). This algorithm achieves an approximation ratio arbitrarily close to the best non private approximation algorithm, improving upon previously known algorithms that only guarantee large (constant) approximation ratios. Furthermore, this is the first constant-factor approximation algorithm for k-means that requires only one round of communication in the local DP model, positively resolving an open question of Stemmer (2020). Our algorithmic framework is quite flexible; we demonstrate this by showing that it also yields a similar near-optimal approximation algorithm in the (one-round) shuffle DP model.

show abstract

“…Due to the importance of DP-FL-SS, it attracts lots of attention from academia and Industries [Balcer et al (2020)]. Up to date, there are some published papers on this topic.…”

Section: Related Work On Dp-fl With Shuffle Model(s)mentioning

confidence: 99%

Recent Progress of Differentially Private Federated Learning With the Shuffle Model

Ahmed

Dushime

et al. 2021

Int. J. Eng. Tech. Mgmt. Res.

View full text Add to dashboard Cite

The emerging of shuffle model has attracted considerable attention of scientists owing to his unique properties in solving the privacy problems in federated learning, specifically the trade off problem between privacy and utility in central and local model. Where, the central model relies on a trusted server which collects users’ raw data and then perturbs it. While in the local model all users perturb their data locally then they send their perturbed data to server. Both models have pron and con. The server in central model enjoys with high accuracy but the users suffer from insufficient privacy in contrast, the local model which provides sufficient privacy at users’ side but the server suffers from limited accuracy. Shuffle model has advanced property of hide position of input messages by perturbing it with perturbation π. Therefore, the scientists considered on adding shuffle model between users and servers to make the server untrusted where the users communicate with the server through the shuffle and boosting the privacy by adding perturbation π for users’ messages without increasing the noise level. Consequently, the usage of modified technique differential privacy federated learning with shuffle model will explores the gap between privacy and accuracy in both models. So this new model attracted many researchers in recent work. In this review, we initiate the analytic learning of a shuffled model for distributed differentially private mechanisms. We focused on the role of shuffle model for solving the problem between privacy and accuracy by summarizing the recent researches about shuffle model and its practical results. Furthermore, we present two types of shuffle, single shuffle and m shuffles with the statistical analysis for each one in boosting the privacy amplification of users with the same level of accuracy by reasoning the practical results of recent papers.

show abstract

Connecting Robust Shuffle Privacy and Pan-Privacy

Cited by 25 publications

References 0 publications

Multiparty Reach and Frequency Histogram: Private, Secure, and Practical

Multiparty Reach and Frequency Histogram: Private, Secure, and Practical

Locally Private k-Means in One Round

Recent Progress of Differentially Private Federated Learning With the Shuffle Model

Contact Info

Product

Resources

About