Calibrating Data to Sensitivity in Private Data Analysis

@article{Proserpio2014CalibratingDT,
  title={Calibrating Data to Sensitivity in Private Data Analysis},
  author={Davide Proserpio and Sharon Goldberg and Frank McSherry},
  journal={Proc. VLDB Endow.},
  year={2014},
  volume={7},
  pages={637-648}
}
We present an approach to differentially private computation in which one does not scale up the magnitude of noise for challenging queries, but rather scales down the contributions of challenging records. While scaling down all records uniformly is equivalent to scaling up the noise magnitude, we show that scaling records non-uniformly can result in substantially higher accuracy by bypassing the worst-case requirements of differential privacy for the noise magnitudes. This paper details the… 
wPINQ: Differentially-Private Analysis of Weighted Datasets
We present an approach to differentially private computation in which one does not scale up the magnitude of noise for challenging queries, but rather scales down the contributions of challenging
Algorithms for synthetic data release under differential privacy
TLDR
Three novel solutions for complex data publication under differential privacy are introduced, namely, PrivBayes, PrivTree and the ladder framework, which enable the private release of a wide range of data types and improve the utility of released data by introducing significantly less perturbations in data modelling.
Differentially Private Publishing of High-dimensional Data Using Sensitivity Control
TLDR
This paper presents DPSense, an approach to publish statistical information from datasets under differential privacy via sensitivity control, and introduces a novel low-sensitivity quality function that enables one to effectively choose a contribution limit while satisfying differential privacy.
Maximum Likelihood Postprocessing for Differential Privacy under Consistency Constraints
TLDR
This paper forms this post-processing step as a constrained maximum likelihood estimation problem, which is equivalent to constrained L1 minimization, and presents a faster generic recipe that is suitable for a wide variety of applications including differentially private contingency tables, histograms, and the matrix mechanism.
APEx: Accuracy-Aware Differentially Private Data Exploration
TLDR
This work presents APEx, a novel system that allows data analysts to pose adaptively chosen sequences of queries along with required accuracy bounds and returns query answers to the data analyst that meet the accuracy bounds, and proves to theData owner that the entire data exploration process is differentially private.
Coupling Dimensionality Reduction with Generative Model for Non-Interactive Private Data Release
TLDR
The PCA-Gauss system is proposed that leverages the novel combination of dimensionality reduction and generative model for synthesizing differentially private data and can serve as a key enabler for real-world deployment of privacy-preserving data release.
When the Signal is in the Noise: Exploiting Diffix's Sticky Noise
TLDR
This paper presents a new class of noise-exploitation attacks, exploiting the noise added by the system to infer private information about individuals in the dataset, and argues that Diffix alone fails to satisfy Art. 29 WP's definition of anonymization.
RON-Gauss: Enhancing Utility in Non-Interactive Private Data Release
TLDR
This work proposes the RON-Gauss model, a novel combination of dimensionality reduction via random orthonormal (RON) projection and the Gaussian generative model for synthesizing differentially-private data that outperforms previous approaches by up to an order of magnitude and can serve as a key enabler for real-world deployment of privacy-preserving data release.
Private Release of Graph Statistics using Ladder Functions
TLDR
A new method which guarantees differential privacy is introduced, which specifies a probability distribution over possible outputs that is carefully defined to maximize the utility for the given input, while still providing the required privacy level.
Differentially Private Data Analysis
The essential task of differentially private data analysis is extending the current non-private algorithms to differentially private algorithms. This extension can be realized by several frameworks,
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
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.
Smooth sensitivity and sampling in private data analysis
TLDR
This is the first formal analysis of the effect of instance-based noise in the context of data privacy, and shows how to do this efficiently for several different functions, including the median and the cost of the minimum spanning tree.
Optimizing linear counting queries under differential privacy
TLDR
The matrix mechanism is proposed, a new algorithm for answering a workload of predicate counting queries and the problem of computing the optimal query strategy in support of a given workload can be formulated as a rank-constrained semidefinite program.
Differentially private data analysis of social networks via restricted sensitivity
TLDR
Using restricted sensitivity, the notion of restricted sensitivity as an alternative to global and smooth sensitivity to improve accuracy in differentially private data analysis is introduced and the usefulness of this notion is demonstrated by considering the task of answering queries regarding social-networks, which is a combination of a graph and a labeling of its vertices.
Relationship privacy: output perturbation for queries with joins
TLDR
An algorithm is proposed that significantly improves utility over competing techniques, typically reducing the error bound from polynomial in the number of nodes to polylogarithmic, and guarantees privacy against adversaries in this class whose prior distribution is numerically bounded.
Recursive mechanism: towards node differential privacy and unrestricted joins
TLDR
A novel differentially private mechanism that supports unrestricted joins is proposed, to release an approximation of a linear statistic of the result of some positive relational algebra calculation over a sensitive database.
Linear dependent types for differential privacy
TLDR
DFuzz is presented, an extension of Fuzz with a combination of linear indexed types and lightweight dependent types that allows a richer sensitivity analysis that is able to certify a larger class of queries as differentially private, including ones whose sensitivity depends on runtime information.
Distance makes the types grow stronger: a calculus for differential privacy
TLDR
This work proposes to streamline the proving of algorithms to be differentially private one at a time with a functional language whose type system automatically guarantees differential privacy, allowing the programmer to write complex privacy-safe query programs in a flexible and compositional way.
Analyzing Graphs with Node Differential Privacy
TLDR
A generic, efficient reduction is derived that allows us to apply any differentially private algorithm for bounded-degree graphs to an arbitrary graph, based on analyzing the smooth sensitivity of the 'naive' truncation that simply discards nodes of high degree.
GUPT: privacy preserving data analysis made easy
TLDR
The design and evaluation of a new system, GUPT, that guarantees differential privacy to programs not developed with privacy in mind, makes no trust assumptions about the analysis program, and is secure to all known classes of side-channel attacks.
...
1
2
3
...