Private Summation in the Multi-Message Shuffle Model

Balle, Borja; Bell, James; Gascón, Adrià; Nissim, Kobbi

doi:10.1145/3372297.3417242

Cited by 56 publications

(58 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this subsection, we shall introduce the private multi messages FL via m parallel shuffles models [Balle et al (2020)]. In this type, m parallel shuffles have been introduced to receive multi messages from each user instead of using single shuffle, which further improves the accuracy and communication more than using single shuffle.…”

Section: The Private Multi Messages Fl Via M Parallel Shuffle Modelsmentioning

confidence: 99%

“…Definition 6. (The Communication model of multi messages in m parallel shuffles models [Balle et al (2020)]): The protocol which presents this communication model of multi messages in m parallel shuffle is P = (R, A) if let D be the user dataset, where D = (D1, D2, ……, Dk). Each user i randomizes its own sensitive data by using local randomization to obtain vector of messages Y= (y1, y2,…….., yk)= R(Dk).…”

Section: The Private Multi Messages Fl Via M Parallel Shuffle Modelsmentioning

confidence: 99%

“…Definition 7 (DP-m shuffles [Balle et al (2020)]): Assume that the mechanism ϒR = ЅЅ m , R m (D), is the analyzer view as an implementation of the protocol P(D). We can say that the mechanism ℳp (D) guarantees (ε, δ)-DP if for every two adjacent datasets D, D', and all output S ⊆Range (ϒR),…”

Section: The Private Multi Messages Fl Via M Parallel Shuffle Modelsmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: The Private Multi Messages Fl Via M Parallel Shuffle Modelsmentioning

confidence: 99%

Section: The Private Multi Messages Fl Via M Parallel Shuffle Modelsmentioning

confidence: 99%

Section: The Private Multi Messages Fl Via M Parallel Shuffle Modelsmentioning

confidence: 99%

See 1 more Smart Citation

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

show abstract

“…This "shuffling" enables users to achieve improved DP guarantees over their LM guarantees in isolation. Several works have since improved the original analyses and expanded the shuffle model to achieve even greater improvements in the users' DP guarantee [6,7,[30][31][32][33].…”

Section: Other Work In Hybrid Trust Modelsmentioning

confidence: 99%

“…Unless all LM users are non-adversarial, the TCM users gain no further benefit from the incorporation of the LM users' privacy noise. Conversely, the LM users may experience privacy amplification through the combination of their locally-added noise; however, this is solely due to intra-group interaction in the LM, and related topics are currently an active area of research on the LM [5,6,16,19,26,33].…”

Section: Blender Amplificationmentioning

confidence: 99%

The Power of the Hybrid Model for Mean Estimation

Avent

Dubey

Korolova

2020

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

We explore the power of the hybrid model of differential privacy (DP), in which some users desire the guarantees of the local model of DP and others are content with receiving the trusted-curator model guarantees. In particular, we study the utility of hybrid model estimators that compute the mean of arbitrary realvalued distributions with bounded support. When the curator knows the distribution’s variance, we design a hybrid estimator that, for realistic datasets and parameter settings, achieves a constant factor improvement over natural baselines.We then analytically characterize how the estimator’s utility is parameterized by the problem setting and parameter choices. When the distribution’s variance is unknown, we design a heuristic hybrid estimator and analyze how it compares to the baselines. We find that it often performs better than the baselines, and sometimes almost as well as the known-variance estimator. We then answer the question of how our estimator’s utility is affected when users’ data are not drawn from the same distribution, but rather from distributions dependent on their trust model preference. Concretely, we examine the implications of the two groups’ distributions diverging and show that in some cases, our estimators maintain fairly high utility. We then demonstrate how our hybrid estimator can be incorporated as a sub-component in more complex, higher-dimensional applications. Finally, we propose a new privacy amplification notion for the hybrid model that emerges due to interaction between the groups, and derive corresponding amplification results for our hybrid estimators.

show abstract

Private Aggregation from Fewer Anonymous Messages

Ghazi

Manurangsi

Pagh

et al. 2020

Advances in Cryptology – EUROCRYPT 2020

View full text Add to dashboard Cite

Consider the setup where n parties are each given an element in the finite field and the goal is to compute the sum in a secure fashion and with as little communication as possible. We study this problem in the anonymized model of Ishai et al. (FOCS 2006) where each party may broadcast anonymous messages on an insecure channel. We present a new analysis of the one-round “split and mix” protocol of Ishai et al. In order to achieve the same security parameter, our analysis reduces the required number of messages by a multiplicative factor. We also prove lower bounds showing that the dependence of the number of messages on the domain size, the number of parties, and the security parameter is essentially tight. Using a reduction of Balle et al. (2019), our improved analysis of the protocol of Ishai et al. yields, in the same model, an -differentially private protocol for aggregation that, for any constant and any , incurs only a constant error and requires only a constant number of messages per party. Previously, such a protocol was known only for messages per party.

show abstract

Private Summation in the Multi-Message Shuffle Model

Cited by 56 publications

References 10 publications

Recent Progress of Differentially Private Federated Learning With the Shuffle Model

Recent Progress of Differentially Private Federated Learning With the Shuffle Model

The Power of the Hybrid Model for Mean Estimation

Private Aggregation from Fewer Anonymous Messages

Contact Info

Product

Resources

About