Concentrated Differential Privacy

By Cynthia Dwork, Guy N. Rothblum. 2016

499 citations recorded by the source corpus.

We introduce Concentrated Differential Privacy, a relaxation of Differential Privacy enjoying better accuracy than both pure differential privacy and its popular "(epsilon,delta)" relaxation without compromising on cumulative privacy loss over multiple computations.

Subfields: Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Privacy & Security

Citations in the corpus

Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning (2017, background): “Several works have adopted DP as an efficient defense mechanism such as [5, 7, 11, 12, 18, 23, 24, 37, 53, 60, 65, 72, 86].”
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data (2016, methodology): “The moments accountant was introduced by Abadi et al. (2016), building on previous work (Bun & Steinke, 2016; Dwork & Rothblum, 2016; Mironov, 2016).”
Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy (2020, background): “Moreover, new DP mechanisms such as RAPPOR [46] will be added, together with relaxations of DP such as Concentrated DP [47] or RÃl’nyi DP [48].”
Rényi Differential Privacy of the Sampled Gaussian Mechanism (2019, methodology): “Concentrated Differential Privacy (CDP) [DR16] and its reformulation, zero-CDP, due to Bun and Steinke [BS16] were developed to reﬁne composition theorems using the Gaussian mechanism as their main motivating examples.”
Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis (2019, background): “Concentrated differential privacy (CDP) is introduced by Dwork and Rothblum [9] as a generalization of differential privacy which provides sharper analysis of many privacy-preserving computations.”
Protection Against Reconstruction and Its Applications in Private Federated Learning (2018, background): “Other variants of privacy require that likelihood ratios are near one on average, and include concentrated and Rényi differential privacy [33, 18, 59].”
Privacy Amplification by Iteration (2018, neutral): “Starting with Concentrated Differential Privacy [DR16], deﬁnitions that allow more ﬁne-grained con-trol of the privacy loss random variable have proven useful.”
Subsampled Rényi Differential Privacy and Analytical Moments Accountant (2018, background): “It offers a unified view of the -differential privacy (pure DP), ( , δ)-differential privacy (approximate DP), and the related notion of Concentrated Differential Privacy (Dwork and Rothblum, 2016; Bun and Steinke, 2016).”
Rényi Differential Privacy (2017, background): “The closely related work by Dwork and Rothblum [9], followed by Bun and Steinke [10], explore privacy definitions—Concentrated Differential Privacy and zero-Concentrated Differential Privacy—that are framed using the language of, respectively, subgaussian tails and the Rényi divergence.”
Scalable Private Learning with PATE (2018, methodology): “To capture this effect quantitatively, Papernot et al. (2017) rely on the moments accountant, introduced by Abadi et al. (2016) and building on previous work (Bun & Steinke, 2016; Dwork & Rothblum, 2016).”
A Hybrid Approach to Privacy-Preserving Federated Learning (2018, methodology): “When an algorithm requires multiple additive noise mechanisms, the evaluation of the privacy guarantee follows from the basic composition theorem [14, 15] or from advanced composition theorems and their extensions [7, 17, 18, 23].”
Advanced Probabilistic Couplings for Differential Privacy (2016, neutral): “For the future, it would be interesting to explore generalizations of differential privacy like the recent notion of concentrated differential privacy [12, 18].”
Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences (2018, background): “This bound is often used to derive (ε, δ)-DP guarantees from other notions of privacy defined in terms of the moment generating function of the privacy loss random variable, including concentrated DP [Dwork and Rothblum, 2016], zero-concentrated DP [Bun and Steinke, 2016], Rényi DP [Mironov, 2017], ”
Differentially Private Model Publishing for Deep Learning (2019, methodology): “An alternative formulation of CDP to Dwork and Rothblum’s (µ, τ)-CDP is proposed by Bun and Steinke [9], called “zero-concentrated differential privacy” (zCDP for short).”