Corpus ID: 14861086

Concentrated Differential Privacy

@article{Dwork2016ConcentratedDP,
  title={Concentrated Differential Privacy},
  author={C. Dwork and G. N. Rothblum},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.01887}
}
  • C. Dwork, G. N. Rothblum
  • Published 2016
  • Computer Science, Mathematics
  • ArXiv
  • We introduce Concentrated Differential Privacy, a relaxation of Differential Privacy enjoying better accuracy than both pure differential privacy and its popular "(epsilon,delta)" relaxation without compromising on cumulative privacy loss over multiple computations. 
    192 Citations

    Topics from this paper

    Rényi Differential Privacy
    • Ilya Mironov
    • Computer Science
    • 2017 IEEE 30th Computer Security Foundations Symposium (CSF)
    • 2017
    • 310
    • PDF
    Composable and versatile privacy via truncated CDP
    • 54
    • PDF
    Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
    • 261
    • PDF
    Improving Laplace Mechanism of Differential Privacy by Personalized Sampling
    Renyi Differential Privacy Mechanisms for Posterior Sampling
    • 32
    • PDF
    Individual Differential Privacy: A Utility-Preserving Formulation of Differential Privacy Guarantees
    • 44
    • PDF
    Information-theoretic metrics for Local Differential Privacy protocols
    • 8
    • PDF
    Bayesian Differential Privacy for Machine Learning
    • 6
    • PDF
    Optimal Differentially Private Mechanisms for Randomised Response
    • 27
    • PDF

    References

    SHOWING 1-10 OF 13 REFERENCES
    Differential privacy and robust statistics
    • 427
    • PDF
    The Composition Theorem for Differential Privacy
    • 231
    • PDF
    The Complexity of Computing the Optimal Composition of Differential Privacy
    • 44
    • PDF
    Differential Privacy
    • 3,804
    • PDF
    The price of privacy and the limits of LP decoding
    • 194
    • PDF
    Revealing information while preserving privacy
    • 875
    • PDF
    Boosting and Differential Privacy
    • 577
    • PDF