Differential Privacy: A Survey of Results

By Cynthia Dwork. 2008

4,153 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability, Safety, Robustness & Interpretability

How researchers see this paper

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

In Artificial Intelligence

In Statistics and Probability

In Safety, Robustness & Interpretability

Citations in the corpus

Model Cards for Model Reporting (2018, background): “As such, collaboration with policy, privacy, and legal experts is necessary in order to ascertain which groups may be responsibly inferred, and how that information should be stored and accessed (for example, using differential privacy [12]).”
Extracting Training Data from Large Language Models (2020, background): “Differential privacy (DP) [11, 12] is a well-established notion of privacy that offers strong guarantees on the privacy of individual records in the training dataset.”
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks (2018, background): “Differential privacy [13,15,16] is a property that an algorithm can satisfy which bounds the information it can leak about its inputs.”
Towards the Science of Security and Privacy in Machine Learning (2016, neutral): “Note that this result (presented below) is analogous to the no free lunch result in data privacy that captures the tension between utility and privacy [115], [116].”
Advances and Open Problems in Federated Learning (2019, background): “The state-of-the-art model for quantifying and limiting information disclosure about individuals is differential privacy (DP) [147, 144, 145], which aims to introduce a level of uncertainty into the released model sufficient to mask the contribution of any individual user.”
How To Backdoor Federated Learning (2018, methodology): “e to the global model using Eq. 4. 6.3 Participant-level differential privacy Recent work [24] showed how to use federated learning for next-word prediction with participantlevel differential privacy [1, 10]. We do not target privacy, but two key steps of differentially private training may limit th”
Kernel Mean Embedding of Distributions: A Review and Beyonds (2016, background): “(2015) and Dziugaite et al. (2015). Deep generative models are neural networks that provide a distribution from which one can generate samples by feeding the models with random noise Z. Generative Adversarial Networks (GAN) proposed by Goodfellow et al. (2014) is one of the most popular deep generat”
DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks (2020, methodology): “These mechanisms are sometimes built under the framework of differential privacy [16] or its derivatives [64, 65].”
Byzantine-Resilient Secure Federated Learning (2020, background): “Although our focus is not on differential-privacy, our approach may in principle be combined with differential privacy techniques [27], which is an interesting future direction.”
Salvaging Federated Learning by Local Adaptation (2020, background): “Differential privacy (Dwork, 2008; 2011) has been promoted as the solution to privacy problems in deep learning (Abadi et al.”
Theoretical Guarantees for Model Auditing with Finite Adversaries (2019, background): “This, in turn, led to the development of diﬀerential privacy (DP): a mathematically rigorous notion of privacy that prevents such memorization by placing an upper bound ε on the worst-case information loss [10–12].”
Real-World Image Datasets for Federated Learning (2019, background): “Differential Privacy, proposed by Dwork in 2006 [ Dwork, 2008 ] , protects user data by adding noise, but incurs a trade-off between model accuracy and the risk of data leakage.”
Learning Privately over Distributed Features: An ADMM Sharing Approach (2019, methodology): “To further provide privacy guarantees, we present a privacy-preserving version of the ADMM sharing algorithm, in which the transmitted value from each party is perturbed by a carefully designed Gaussian noise to achieve the notion of ǫ, δ -differential privacy Dwork (2008); Dwork et al. (2014).”
Federated Heavy Hitters Discovery with Differential Privacy (2019, background): “Diﬀerential privacy (DP) is a rigorous privacy notion that has been carefully studied over the last decade (Dwork et al., 2006b,a; Dwork, 2008; Dwork and Roth, 2014) and widely adopted in industry (Ding et al., 2017; Apple, 2017; Kenthapadi and Tran, 2018; Erlingsson et al., 2014).”
Federated Machine Learning (2019, background): “h semi-honest and malicious assumptions. These works require participants’ data to be secretly-shared among non-colluding servers. DifferentialPrivacy.AnotherlineofworkusetechniquesDifferentialPrivacy[18]ork-Anonymity [63] for data privacy protection [1, 12, 42, 61]. The methods of differential priv”
SecureBoost: A Lossless Federated Learning Framework (2019, methodology): “For example, Apple proposed to use differential privacy (Dwork, Roth, and others 2014; Dwork 2008) to address the privacy preservation issue.”
Inference Under Information Constraints I: Lower Bounds From Chi-Square Contraction (2018, neutral): “[21], [35], [9], [19]): For ρ > 0, W (y | x1) W (y | x2) ≤ e, ∀x1, x2 ∈ [k],∀y ∈ {0, 1}∗.”
Detecting Violations of Differential Privacy (2018, background): “49 Correct Exponential Noisy Max [15] 4.”