A Multiplicative Weights Mechanism for Privacy-Preserving Data Analysis

@article{Hardt2010AMW,
  title={A Multiplicative Weights Mechanism for Privacy-Preserving Data Analysis},
  author={Moritz Hardt and Guy N. Rothblum},
  journal={2010 IEEE 51st Annual Symposium on Foundations of Computer Science},
  year={2010},
  pages={61-70}
}
  • Moritz Hardt, G. 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… Expand
Private data release via learning thresholds
TLDR
The task of analyzing a database containing sensitive information about individual participants is studied, and a computationally efficient reduction from differentially private data release for a class of counting queries, to learning thresholded sums of predicates from a related class is instantiated. Expand
A study of privacy and fairness in sensitive data analysis
In this thesis we consider the challenges arising in the design of algorithms that interact with sensitive personal data—such as medical records, online tracking data, or financial records. OneExpand
Optimal error of query sets under the differentially-private matrix mechanism
TLDR
A novel lower bound on the minimum total error required to simultaneously release answers to a set of workload queries is revealed, revealing that the hardness of a query workload is related to the spectral properties of the workload when it is represented in matrix form. Expand
Measuring the achievable error of query sets under differential privacy
TLDR
A novel lower bound on the minimum total error required to simultaneously release answers to a set of workload queries is revealed, which reveals that the hardness of a query workload is related to the spectral properties of the workload when it is represented in matrix form. Expand
Lower Bounds on the Error of Query Sets Under the Differentially-Private Matrix Mechanism
TLDR
A novel lower bound on the minimum total error required to simultaneously release answers to a set of workload queries when using the matrix mechanism is revealed and reveals that the hardness of a query workload is related to the spectral properties of the workload when it is represented in matrix form. Expand
Integrating historical noisy answers for improving data utility under differential privacy
TLDR
This work proposes to integrate all available linear query answers into a consistent form that embodies the knowledge learned from the noisy answers, obtaining more accurate answers to past queries and even new queries, improving the data utility. Expand
Differential privacy for the analyst via private equilibrium computation
TLDR
This work gives new mechanisms for answering exponentially many queries from multiple analysts on a private database, while protecting privacy both for the individuals in the database and for the analysts, and is the first to offer differential privacy on the joint distribution over analysts' answers. Expand
Upper and Lower Bounds for Privacy and Adaptivity in Algorithmic Data Analysis
TLDR
An alternative definition of differential privacy is given, which is a formal privacy standard for protecting sensitive data, and lower bounds in the adaptive data analysis setting that nearly match the upper bounds given by differential privacy are proved. Expand
Privacy and the Complexity of Simple Queries
TLDR
A sharp upper bound on the number of linear queries that can be accurately answered while satisfying differential privacy by an efficient algorithm is shown, assuming the existence of cryptographic traitor-tracing schemes. Expand
A Teaser for Differential Privacy
Differential privacy is a formal mathematical definition of privacy in the context of privacypreserving data analysis. It enables a trusted data curator to release global statistical informationExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 20 REFERENCES
Interactive privacy via the median mechanism
TLDR
The median mechanism is the first privacy mechanism capable of identifying and exploiting correlations among queries in an interactive setting, and an efficient implementation is given, with running time polynomial in the number of queries, the database size, and the domain size. Expand
On the complexity of differentially private data release: efficient algorithms and hardness results
TLDR
Private data analysis in the setting in which a trusted and trustworthy curator releases to the public a "sanitization" of the data set that simultaneously protects the privacy of the individual contributors of data and offers utility to the data analyst is considered. Expand
Calibrating Noise to Sensitivity in Private Data Analysis
TLDR
The study is extended to general functions f, proving that privacy can be preserved by calibrating the standard deviation of the noise according to the sensitivity of the function f, which is the amount that any single argument to f can change its output. Expand
Differential privacy under continual observation
TLDR
This work identifies the problem of maintaining a counter in a privacy preserving manner and shows its wide applicability to many different problems. Expand
New Efficient Attacks on Statistical Disclosure Control Mechanisms
TLDR
The Dinur-Nissim style results are strong because they demonstrate insecurity of all low-distortion privacy mechanisms, and a more acute attack, requiring only a fixed number of queries for each bit revealed. Expand
On the geometry of differential privacy
TLDR
The lower bound is strong enough to separate the concept of differential privacy from the notion of approximate differential privacy where an upper bound of O(√{d}/ε) can be achieved. Expand
Privacy-Preserving Datamining on Vertically Partitioned Databases
TLDR
Under a rigorous definition of breach of privacy, Dinur and Nissim proved that unless the total number of queries is sub-linear in the size of the database, a substantial amount of noise is required to avoid a breach, rendering the database almost useless. Expand
PCPs and the Hardness of Generating Private Synthetic Data
TLDR
It is shown that there is no polynomial-time, differentially private algorithm A that takes a database D and outputs a "synthetic database" D all of whose two-way marginals are approximately equal to those of D. Expand
Boosting and Differential Privacy
TLDR
This work obtains an $O(\eps^2) bound on the {\em expected} privacy loss from a single $\eps$-\dfp{} mechanism, and gets stronger bounds on the expected cumulative privacy loss due to multiple mechanisms, each of which provides $\eps-differential privacy or one of its relaxations, and each ofWhich operates on (potentially) different, adaptively chosen, databases. Expand
Revealing information while preserving privacy
TLDR
A polynomial reconstruction algorithm of data from noisy (perturbed) subset sums and shows that in order to achieve privacy one has to add perturbation of magnitude (Ω√<i>n</i>). Expand
...
1
2
...