A Multiplicative Weights Mechanism for Privacy-Preserving Data Analysis

@article{Hardt2010AMW,
  title={A Multiplicative Weights Mechanism for Privacy-Preserving Data Analysis},
  author={M. Hardt and G. N. Rothblum},
  journal={2010 IEEE 51st Annual Symposium on Foundations of Computer Science},
  year={2010},
  pages={61-70}
}
  • M. Hardt, G. N. Rothblum
  • Published 2010
  • Computer Science
  • 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
  • We consider statistical data analysis in the interactive setting. In this setting a trusted curator maintains a database of sensitive information about individual participants, and releases privacy-preserving answers to queries as they arrive. Our primary contribution is a new differentially private multiplicative weights mechanism for answering a large number of interactive counting (or linear) queries that arrive online and may be adaptively chosen. This is the first mechanism with worst-case… CONTINUE READING
    331 Citations
    Private data release via learning thresholds
    • 49
    • PDF
    Optimal error of query sets under the differentially-private matrix mechanism
    • 34
    • Highly Influenced
    • PDF
    Lower Bounds on the Error of Query Sets Under the Differentially-Private Matrix Mechanism
    • 2
    • PDF
    Integrating historical noisy answers for improving data utility under differential privacy
    • 6
    • PDF
    Differential privacy for the analyst via private equilibrium computation
    • 30
    • Highly Influenced
    • PDF
    Privacy and the Complexity of Simple Queries
    • Highly Influenced
    A Teaser for Differential Privacy
    • 2
    • PDF

    References

    SHOWING 1-10 OF 20 REFERENCES
    Interactive privacy via the median mechanism
    • 248
    • Highly Influential
    • PDF
    On the complexity of differentially private data release: efficient algorithms and hardness results
    • 308
    • PDF
    Calibrating Noise to Sensitivity in Private Data Analysis
    • 4,072
    • PDF
    Differential privacy under continual observation
    • 447
    • PDF
    New Efficient Attacks on Statistical Disclosure Control Mechanisms
    • 97
    • PDF
    On the geometry of differential privacy
    • 289
    • PDF
    A learning theory approach to non-interactive database privacy
    • 490
    • PDF
    Privacy-Preserving Datamining on Vertically Partitioned Databases
    • 373
    • Highly Influential
    • PDF
    PCPs and the Hardness of Generating Private Synthetic Data
    • 72
    • PDF
    Boosting and Differential Privacy
    • 576
    • PDF