Boosting and Differential Privacy

@article{Dwork2010BoostingAD,
  title={Boosting and Differential Privacy},
  author={C. Dwork and G. N. Rothblum and S. Vadhan},
  journal={2010 IEEE 51st Annual Symposium on Foundations of Computer Science},
  year={2010},
  pages={51-60}
}
  • C. Dwork, G. N. Rothblum, S. Vadhan
  • Published 2010
  • Computer Science
  • 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
  • Boosting is a general method for improving the accuracy of learning algorithms. We use boosting to construct improved {\em privacy-preserving synopses} of an input database. These are data structures that yield, for a given set $\Q$ of queries over an input database, reasonably accurate estimates of the responses to every query in~$\Q$, even when the number of queries is much larger than the number of rows in the database. Given a {\em base synopsis generator} that takes a distribution on $\Q… CONTINUE READING
    576 Citations

    Figures and Topics from this paper

    The Geometry of Differential Privacy: The Small Database and Approximate Cases
    • 16
    Differentially Private Data Releasing for Smooth Queries with Synthetic Database Output
    • 1
    • PDF
    Between Pure and Approximate Differential Privacy
    • 65
    • PDF
    The Price of Selection in Differential Privacy
    • 17
    • PDF
    A learning theory approach to noninteractive database privacy
    • 250
    • PDF
    Strong Hardness of Privacy from Weak Traitor Tracing
    • 8
    • PDF
    Efficient Algorithms for Privately Releasing Marginals via Convex Relaxations
    • 25
    • PDF
    Faster Algorithms for Privately Releasing Marginals
    • 37
    • PDF
    Closure Properties for Private Classification and Online Prediction
    • 6
    • PDF

    References

    SHOWING 1-10 OF 36 REFERENCES
    Practical privacy: the SuLQ framework
    • 761
    • PDF
    A Multiplicative Weights Mechanism for Privacy-Preserving Data Analysis
    • 331
    • PDF
    The uniform hardcore lemma via approximate Bregman projections
    • 47
    • PDF
    Calibrating Noise to Sensitivity in Private Data Analysis
    • 4,080
    • PDF
    Privacy in Search Logs
    • 34
    • PDF
    Our Data, Ourselves: Privacy Via Distributed Noise Generation
    • 1,139
    • PDF
    A learning theory approach to non-interactive database privacy
    • 490
    • Highly Influential
    • PDF
    Privacy-preserving logistic regression
    • 440
    • PDF
    On the complexity of differentially private data release: efficient algorithms and hardness results
    • 308
    • PDF