Smooth sensitivity and sampling in private data analysis
Proceedings of the thirty-ninth annual ACM symposium on Theory of computing
Privacy, accuracy, and consistency too: a holistic solution to contingency table release
Proceedings of the twenty-sixth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Privacy-Preserving Data Mining: Models and Algorithms
Privacy-Preserving Data Mining: Models and Algorithms
Differential privacy and robust statistics
Proceedings of the forty-first annual ACM symposium on Theory of computing
Relationship privacy: output perturbation for queries with joins
Proceedings of the twenty-eighth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Privacy integrated queries: an extensible platform for privacy-preserving data analysis
Proceedings of the 2009 ACM SIGMOD International Conference on Management of data
Accurate Estimation of the Degree Distribution of Private Networks
ICDM '09 Proceedings of the 2009 Ninth IEEE International Conference on Data Mining
Data mining with differential privacy
Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining
A firm foundation for private data analysis
Communications of the ACM
Proceedings of the 2011 ACM SIGMOD International Conference on Management of data
Differentially private data cubes: optimizing noise sources and consistency
Proceedings of the 2011 ACM SIGMOD International Conference on Management of data
Calibrating noise to sensitivity in private data analysis
TCC'06 Proceedings of the Third conference on Theory of Cryptography
Hi-index | 0.00 |
Enabling accurate analysis of social network data while preserving differential privacy has been challenging since graph features such as clustering coefficient or modularity often have high sensitivity, which is different from traditional aggregate functions (e.g., count and sum) on tabular data. In this paper, we treat a graph statistics as a function $f$ and develop a divide and conquer approach to enforce differential privacy. The basic procedure of this approach is to first decompose the target computation $f$ into several less complex unit computations $f1, \cdots, f_m$ connected by basic mathematical operations (e.g., addition, subtraction, multiplication, division), then perturb the output of each $f_i$ with Lap lace noise derived from its own sensitivity value and the distributed privacy threshold $\epsilon_i$, and finally combine those perturbed $f_i$ as the perturbed output of computation $f$. We examine how various operations affect the accuracy of complex computations. When unit computations have large global sensitivity values, we enforce the differential privacy by calibrating noise based on the smooth sensitivity, rather than the global sensitivity. By doing this, we achieve the strict differential privacy guarantee with smaller magnitude noise. We illustrate our approach by using clustering coefficient, which is a popular statistics used in social network analysis. Empirical evaluations show the developed divide and conquer approach outperforms the direct approach.