DeepAI AI Chat
Log In Sign Up

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

by   Vitaly Feldman, et al.

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta [EFMRTT19] demonstrates that random shuffling amplifies differential privacy guarantees of locally randomized data. Such amplification implies substantially stronger privacy guarantees for systems in which data is contributed anonymously [BEMMRLRKTS17] and has lead to significant interest in the shuffle model of privacy [CSUZZ19,EFMRTT19]. We show that random shuffling of n data records that are input to ε_0-differentially private local randomizers results in an (O((1-e^-ε_0)√(e^ε_0log(1/δ)/n)), δ)-differentially private algorithm. This significantly improves over previous work and achieves the asymptotically optimal dependence in ε_0. Our result is based on a new approach that is simpler than previous work and extends to approximate differential privacy with nearly the same guarantees. Our work also yields an empirical method to derive tighter bounds the resulting ε and we show that it gets to within a small constant factor of the optimal bound. As a direct corollary of our analysis, we derive a simple and asymptotically optimal algorithm for discrete distribution estimation in the shuffle model of privacy. We also observe that our result implies the first asymptotically optimal privacy analysis of noisy stochastic gradient descent that applies to sampling without replacement.


page 1

page 2

page 3

page 4


Stronger Privacy Amplification by Shuffling for Rényi and Approximate Differential Privacy

The shuffle model of differential privacy has gained significant interes...

Efficiency in local differential privacy

We develop a theory of asymptotic efficiency in regular parametric model...

SA-DPSGD: Differentially Private Stochastic Gradient Descent based on Simulated Annealing

Differential privacy (DP) provides a formal privacy guarantee that preve...

Controlling Privacy Loss in Survey Sampling (Working Paper)

Social science and economics research is often based on data collected i...

Online and Differentially-Private Tensor Decomposition

In this paper, we resolve many of the key algorithmic questions regardin...

Locally Differentially-Private Randomized Response for Discrete Distribution Learning

We consider a setup in which confidential i.i.d. samples X_1,,X_n from a...

Walking to Hide: Privacy Amplification via Random Message Exchanges in Network

The *shuffle model* is a powerful tool to amplify the privacy guarantees...