SuLQ
Practical privacy: the SuLQ framework. We consider a statistical database in which a trusted administrator introduces noise to the query responses with the goal of maintaining privacy of individual database entries. In such a database, a query consists of a pair (S, f) where S is a set of rows in the database and f is a function mapping database rows to {0, 1}. The true answer is ΣiεS f(di), and a noisy version is released as the response to the query. Results of Dinur, Dwork, and Nissim show that a strong form of privacy can be maintained using a surprisingly small amount of noise -- much less than the sampling error -- provided the total number of queries is sublinear in the number of database rows. We call this query and (slightly) noisy reply the SuLQ (Sub-Linear Queries) primitive. The assumption of sublinearity becomes reasonable as databases grow increasingly large.We extend this work in two ways. First, we modify the privacy analysis to real-valued functions f and arbitrary row types, as a consequence greatly improving the bounds on noise required for privacy. Second, we examine the computational power of the SuLQ primitive. We show that it is very powerful indeed, in that slightly noisy versions of the following computations can be carried out with very few invocations of the primitive: principal component analysis, k means clustering, the Perceptron Algorithm, the ID3 algorithm, and (apparently!) all algorithms that operate in the in the statistical query learning model [11].
This software is also peer reviewed by journal TOMS.
This software is also peer reviewed by journal TOMS.
Keywords for this software
References in zbMATH (referenced in 128 articles )
Showing results 1 to 20 of 128.
Sorted by year (- Gilliam, George; Uhan, Nelson A.: Computing payoff allocations in the approximate core of linear programming games in a privacy-preserving manner (2022)
- Beimel, Amos; Nissim, Kobbi; Stemmer, Uri: Learning privately with labeled and unlabeled examples (2021)
- Dekker, F. W.; Erkin, Zekeriya: Privacy-preserving data aggregation with probabilistic range validation (2021)
- Feldman, Vitaly; Guzmán, Cristóbal; Vempala, Santosh: Statistical query algorithms for mean vector estimation and stochastic convex optimization (2021)
- Stemmer, Uri: Locally private (k)-means clustering (2021)
- Bunn, Paul; Ostrovsky, Rafail: Oblivious sampling with applications to two-party (k)-means clustering (2020)
- Ullman, Jonathan; Vadhan, Salil: PCPs and the hardness of generating synthetic data (2020)
- Wang, Di; Xu, Jinhui: Principal component analysis in the local differential privacy model (2020)
- Bun, Mark; Nissim, Kobbi; Stemmer, Uri: Simultaneous private learning of multiple concepts (2019)
- Bun, Mark; Ullman, Jonathan; Vadhan, Salil: Fingerprinting codes and the price of approximate differential privacy (2018)
- Feldman, Vitaly; Perkins, Will; Vempala, Santosh: On the complexity of random satisfiability problems with planted solutions (2018)
- Karwa, Vishesh; Vadhan, Salil: Finite sample differentially private confidence intervals (2018)
- Vadhan, Salil: The complexity of differential privacy (2017)
- Beimel, Amos; Nissim, Kobbi; Stemmer, Uri: Private learning and sanitization: pure vs. approximate differential privacy (2016)
- Bun, Mark; Zhandry, Mark: Order-revealing encryption and the hardness of private learning (2016)
- Choromanska, Anna; Choromanski, Krzysztof; Jagannathan, Geetha; Monteleoni, Claire: Differentially-private learning of low dimensional manifolds (2016)
- Kowalczyk, Lucas; Malkin, Tal; Ullman, Jonathan; Zhandry, Mark: Strong hardness of privacy from weak traitor tracing (2016)
- Ullman, Jonathan: Answering (n^2+o(1)) counting queries with differential privacy is hard (2016)
- Wang, Ke; Wang, Peng; Fu, Ada Waichee; Wong, Raymond Chi-Wing: Generalized bucketization scheme for flexible privacy settings (2016)
- Balcan, Maria Florina; Feldman, Vitaly: Statistical active learning algorithms for noise tolerance and differential privacy (2015)