Corpus ID: 229363581

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

@article{Feldman2020HidingAT,
  title={Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling},
  author={V. Feldman and A. McMillan and Kunal Talwar},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.12803}
}
  • V. Feldman, A. McMillan, Kunal Talwar
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta [EFMRTT19] demonstrates that random shuffling of input data amplifies differential privacy guarantees. Such amplification leads to substantially stronger privacy guarantees for systems in which data is contributed anonymously [BEMMRLRKTS17] and for the analysis of noisy stochastic gradient descent. We show that an ε0-locally differentially private algorithm, under shuffling with n users, amplifies to a (Θ((1 − e−ε0… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 29 REFERENCES
    On the Power of Multiple Anonymous Messages
    • 21
    • PDF
    Heavy Hitters and the Structure of Local Privacy
    • 77
    • PDF
    Distributed Differential Privacy via Shuffling
    • 70
    • PDF
    The Complexity of Computing the Optimal Composition of Differential Privacy
    • 44
    • PDF
    The Algorithmic Foundations of Differential Privacy
    • 2,547
    • PDF
    The Privacy Blanket of the Shuffle Model
    • 59
    • PDF
    Privacy Amplification via Random Check-Ins
    • 4
    • PDF