On the complexity of differentially private data release

Dwork, Cynthia; Naor, Moni; Reingold, Omer; Rothblum, Guy N.; Vadhan, Salil

doi:10.1145/1536414.1536467

Cited by 311 publications

(288 citation statements)

References 20 publications

Supporting

Mentioning

285

Contrasting

Unclassified

Order By: Relevance

“…Also, for fixed ∆(f ), the smaller ε, the more Laplace noise is added: when ε is very small, Definition 1 almost requires that the probabilities on both sides of Equation (1) be equal, which requires the randomized function κ(·) = f (·) + Y (·) to yield very similar results for all pairs of neighbor data sets; adding a lot of noise is a way to achieve this. Differential privacy was also proposed for the non-interactive setting in [27,28,29,30]. Even though a non-interactive data release can be used to answer an arbitrarily large number of queries, in all these proposals, this is obtained at the cost of offering utility guarantees only for a restricted class of queries [27], typically count queries.…”

Section: Definition 1 (ε-Differential Privacy)mentioning

confidence: 99%

“…Moreover, since many works on differential privacy focus on preserving the utility of counting queries [35,31,32,27,28,29,30], we measured how the methods preserve the data distribution by building histograms of each attribute and comparing the distribution between the original and masked values according to the well-known Jensen-Shannon divergence (JSD) [56], which is symmetric and bounded in the 0..1 range. At a data set level, we averaged the divergence of all the attributes.…”

Section: Evaluation Measures and Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

Utility-preserving differentially private data releases via individual ranking microaggregation

2016

View full text Add to dashboard Cite

Being able to release and exploit open data gathered in information systems is crucial for researchers, enterprises and the overall society. Yet, these data must be anonymized before release to protect the privacy of the subjects to whom the records relate. Differential privacy is a privacy model for anonymization that offers more robust privacy guarantees than previous models, such as k-anonymity and its extensions. However, it is often disregarded that the utility of differentially private outputs is quite limited, either because of the amount of noise that needs to be added to obtain them or because utility is only preserved for a restricted type and/or a limited number of queries. On the contrary, k-anonymity-like data releases make no assumptions on the uses of the protected data and, thus, do not restrict the number and type of doable analyses. Recently, some authors have proposed mechanisms to offer general-purpose differentially private data releases. This paper extends such works with a specific focus on the preservation of the utility of the protected data. Our proposal builds on microaggregation-based anonymization, which is more flexible and utility-preserving than alternative anonymization methods used in the literature, in order to reduce the amount of noise needed to satisfy differential privacy. In this way, we improve the utility of differentially private data releases. Moreover, the noise reduction we achieve does not depend on the size of the data set, but just on the number of attributes to be protected, which is a more desirable behavior for large data sets. The utility benefits brought by our proposal are empirically evaluated and compared with related works for several data sets and metrics.

show abstract

Section: Definition 1 (ε-Differential Privacy)mentioning

confidence: 99%

Section: Evaluation Measures and Experimentsmentioning

confidence: 99%

Utility-preserving differentially private data releases via individual ranking microaggregation

2016

View full text Add to dashboard Cite

show abstract

“…The first cryptographic tool we need in our construction is 2-message witness indistinguishable proofs for NP ("zaps") [FS90,DN07] in the plain model (with no common reference string). Consider a language L ∈ NP.…”

Section: Zaps (2-message Wi Proofs)mentioning

confidence: 99%

“…Every language in NP has an extractable zap proof system (P, V, E), as defined in Definition 6, if there exists non-interactive zero-knowledge proofs of knowledge for NP [DN07].…”

Section: Zaps (2-message Wi Proofs)mentioning

confidence: 99%

See 1 more Smart Citation

Separating Computational and Statistical Differential Privacy in the Client-Server Model

Bun

Chen

Vadhan

2016

Theory of Cryptography

Self Cite

View full text Add to dashboard Cite

Abstract. Differential privacy is a mathematical definition of privacy for statistical data analysis. It guarantees that any (possibly adversarial) data analyst is unable to learn too much information that is specific to an individual. Mironov et al. (CRYPTO 2009) proposed several computational relaxations of differential privacy (CDP), which relax this guarantee to hold only against computationally bounded adversaries. Their work and subsequent work showed that CDP can yield substantial accuracy improvements in various multiparty privacy problems. However, these works left open whether such improvements are possible in the traditional client-server model of data analysis. In fact, Groce, Katz and Yerukhimovich (TCC 2011) showed that, in this setting, it is impossible to take advantage of CDP for many natural statistical tasks. Our main result shows that, assuming the existence of sub-exponentially secure one-way functions and 2-message witness indistinguishable proofs (zaps) for NP, that there is in fact a computational task in the clientserver model that can be efficiently performed with CDP, but is infeasible to perform with information-theoretic differential privacy.

show abstract

Adversarial Machine Learning

Reznik¹

2021

Intelligent Security Systems

View full text Add to dashboard Cite

In this paper (expanded from an invited talk at AISEC 2010), we discuss an emerging field of study: adversarial machine learning-the study of effective machine learning techniques against an adversarial opponent. In this paper, we: give a taxonomy for classifying attacks against online machine learning algorithms; discuss application-specific factors that limit an adversary's capabilities; introduce two models for modeling an adversary's capabilities; explore the limits of an adversary's knowledge about the algorithm, feature space, training, and input data; explore vulnerabilities in machine learning algorithms; discuss countermeasures against attacks; introduce the evasion challenge; and discuss privacy-preserving learning techniques.

show abstract

On the complexity of differentially private data release

Cited by 311 publications

References 20 publications

Utility-preserving differentially private data releases via individual ranking microaggregation

Utility-preserving differentially private data releases via individual ranking microaggregation

Separating Computational and Statistical Differential Privacy in the Client-Server Model

Adversarial Machine Learning

Contact Info

Product

Resources

About