Corpus ID: 162183941

Elliptical Perturbations for Differential Privacy

@article{Reimherr2019EllipticalPF,
  title={Elliptical Perturbations for Differential Privacy},
  author={Matthew Reimherr and Jordan Awan},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.09420}
}
  • Matthew Reimherr, Jordan Awan
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • We study elliptical distributions in locally convex vector spaces, and determine conditions when they can or cannot be used to satisfy differential privacy (DP). A requisite condition for a sanitized statistical summary to satisfy DP is that the corresponding privacy mechanism must induce equivalent measures for all possible input databases. We show that elliptical distributions with the same dispersion operator, $C$, are equivalent if the difference of their means lies in the Cameron-Martin… CONTINUE READING

    Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES

    The Optimal Noise-Adding Mechanism in Differential Privacy

    VIEW 1 EXCERPT

    On the geometry of differential privacy

    VIEW 2 EXCERPTS

    Differential privacy for functions and functional data

    VIEW 3 EXCERPTS