Privately releasing conjunctions and the statistical query barrier
Proceedings of the forty-third annual ACM symposium on Theory of computing
Communications of the ACM
Private data release via learning thresholds
Proceedings of the twenty-third annual ACM-SIAM symposium on Discrete Algorithms
An adaptive mechanism for accurate query answering under differential privacy
Proceedings of the VLDB Endowment
Differential privacy in data publication and analysis
SIGMOD '12 Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data
Unconditional differentially private mechanisms for linear queries
STOC '12 Proceedings of the forty-fourth annual ACM symposium on Theory of computing
Optimal private halfspace counting via discrepancy
STOC '12 Proceedings of the forty-fourth annual ACM symposium on Theory of computing
Iterative constructions and private data release
TCC'12 Proceedings of the 9th international conference on Theory of Cryptography
Integrating historical noisy answers for improving data utility under differential privacy
Proceedings of the 15th International Conference on Extending Database Technology
The application of differential privacy to health data
Proceedings of the 2012 Joint EDBT/ICDT Workshops
Faster algorithms for privately releasing marginals
ICALP'12 Proceedings of the 39th international colloquium conference on Automata, Languages, and Programming - Volume Part I
Privacy-aware personalization for mobile advertising
Proceedings of the 2012 ACM conference on Computer and communications security
Empirical evaluation of statistical inference from differentially-private contingency tables
PSD'12 Proceedings of the 2012 international conference on Privacy in Statistical Databases
Is privacy compatible with truthfulness?
Proceedings of the 4th conference on Innovations in Theoretical Computer Science
Differentially private data analysis of social networks via restricted sensitivity
Proceedings of the 4th conference on Innovations in Theoretical Computer Science
Optimal error of query sets under the differentially-private matrix mechanism
Proceedings of the 16th International Conference on Database Theory
A learning theory approach to noninteractive database privacy
Journal of the ACM (JACM)
Publishing trajectories with differential privacy guarantees
Proceedings of the 25th International Conference on Scientific and Statistical Database Management
How robust are linear sketches to adaptive inputs?
Proceedings of the forty-fifth annual ACM symposium on Theory of computing
Beyond worst-case analysis in private singular vector computation
Proceedings of the forty-fifth annual ACM symposium on Theory of computing
Differential privacy for the analyst via private equilibrium computation
Proceedings of the forty-fifth annual ACM symposium on Theory of computing
The geometry of differential privacy: the sparse and approximate cases
Proceedings of the forty-fifth annual ACM symposium on Theory of computing
Answering n{2+o(1)} counting queries with differential privacy is hard
Proceedings of the forty-fifth annual ACM symposium on Theory of computing
Faster private release of marginals on small databases
Proceedings of the 5th conference on Innovations in theoretical computer science
Mechanism design in large games: incentives and privacy
Proceedings of the 5th conference on Innovations in theoretical computer science
Differential privacy based on importance weighting
Machine Learning
| Hi-index | 0.02 |
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 accuracy guarantees that can answer large numbers of interactive queries and is {\em efficient} (in terms of the runtime's dependence on the data universe size). The error is asymptotically \emph{optimal} in its dependence on the number of participants, and depends only logarithmically on the number of queries being answered. The running time is nearly {\em linear} in the size of the data universe. As a further contribution, when we relax the utility requirement and require accuracy only for databases drawn from a rich class of databases, we obtain exponential improvements in running time. Even in this relaxed setting we continue to guarantee privacy for {\em any} input database. Only the utility requirement is relaxed. Specifically, we show that when the input database is drawn from a {\em smooth} distribution — a distribution that does not place too much weight on any single data item — accuracy remains as above, and the running time becomes {\em poly-logarithmic} in the data universe size. The main technical contributions are the application of multiplicative weights techniques to the differential privacy setting, a new privacy analysis for the interactive setting, and a technique for reducing data dimensionality for databases drawn from smooth distributions.