Our Data, Ourselves: Privacy Via Distributed Noise Generation
The DOI matches its Crossref record; 29 of the 31 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Differential privacy (DP) [26] is an alternative theoretical model for protecting the privacy of individual data, which has been widely applied to many areas, not only traditional algorithms, e.g., boosting [27], principal component analysis [15], support vector machine [86], but also deep learning research [1, 70]. It ensures that the addition or removal does not substantially affect the outcome”
From Federated Learning for Healthcare Informatics (2021) · cites this paper as [26]
In the citing paper
“The simplest way to create a DP-mechanism is by adding Gaussian noise to the outcomes of a deterministic function with bounded sensitivity 21 .”
From Federated Learning and Differential Privacy for Medical Image Analysis (2021) · cites this paper as [21]
Citations
Cites
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Self-citationThe Byzantine generals problem
Lamport, L., Shostak, R., & Pease, M. (1982) · ACM Transactions on Programming Languages and Systems · doi:10.1145/357172.357176 · Cited by 6,023 · cited 1×
“We will refer to several well-known primitive building blocks for constructing distributed protocols: Byzantine Agreement [20], Distributed Coin Flipping [22], Verifiable Secret Sharing (VSS) [8], Non-Malleable VSS, and Secure Function Evaluation (SFE) [18].”
Goldreich, O., Micali, S., & Wigderson, A. (1987) · Proceedings of the nineteenth annual ACM conference on Theory of computing - STOC '87 · doi:10.1145/28395.28420 · Cited by 3,590
Protocols for secure computations
Yao, A. C. (1982) · 23rd Annual Symposium on Foundations of Computer Science (sfcs 1982) · doi:10.1109/sfcs.1982.38 · Cited by 3,306
Privacy-preserving data mining
Agrawal, R., & Srikant, R. (2000) · ACM SIGMOD Record · doi:10.1145/335191.335438 · Cited by 2,961
Protocols for secure computations
Yao, A. C.-C. (1982) · doi:10.1109/sfcs.1982.88 · Cited by 2,661
Goldreich, O. (2001) · Cambridge University Press eBooks · doi:10.1017/cbo9780511546891 · Cited by 2,181
Goldreich, O. (2004) · Cambridge University Press eBooks · doi:10.1017/cbo9780511721656 · Cited by 1,805
Foundations of Cryptography: Volume 2, Basic Applications
Goldreich, O. (2004) · Cited by 1,592
On the design and quantification of privacy preserving data mining algorithms
Agrawal, D., & Aggarwal, C. C. (2001) · Proceedings of the twentieth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems · doi:10.1145/375551.375602 · Cited by 1,006 · cited 1×
“accurate statistics about a population while preserving the privacy of individuals [1, 2, 15, 11, 14, 5, 6, 4, 13].”
Cited by
Items 701–800 of 1,008
Chen, Y., Hsu, C., Yu, C.-M., Barhamgi, M., & Perera, C. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3133625 · Cited by 21
“Dwork et al. [14] proposed a loose definition of DP named ( (cid:15) , δ )-DP which allows for the probability that (cid:15) -DP is failed with probability δ and we show it as the following: Definition 1.”
BackgroundPrivTDSI: A Local Differentially Private Approach for Truth Discovery via Sampling and Inference
Zhang, P., Cheng, X., Su, S., & Zhu, B. (2022) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2022.3186175 · Cited by 18
“…al. [14] pro-pose a personalized incentive approach for continuous inputs while satisfying " -KL LDP. Due to the adoption of the gaussian mechanism [42], these two approaches [9], [14] only guarantee weaker versions of LDP. Wang et al. [11] focus on streaming data for truth discovery, and propose…”
BackgroundDistributed Detection of Malicious Android Apps While Preserving Privacy Using Federated Learning
Lee, S. (2023) · Sensors · doi:10.3390/s23042198 · Cited by 18
“In the proposed FL model, it is assumed that the local differential privacy (DP) mechanism [31,32] is applied in the process of collecting raw data within the coalition.”
Reinforced Computer-Aided Framework for Diagnosing Thyroid Cancer
Xie, X., Tian, Y., Ota, K., Dong, M., Liu, Z., Jin, H., & Yao, D. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2023.3251323 · Cited by 19
“In general, a privacy-preserving mechanism M gives ( (cid:4), δ )-differential privacy if satisfying: where D and D (cid:4) are neighboring datasets for outputs Ω , (cid:4) repre-sentstheindistinguishability,balancingaccuracyand δ measures approximate degree [37].”
BackgroundHiebel, N., Ferret, O., Fort, K., & Névéol, A. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.170 · Cited by 48
“Mela-mud and Shivade (2019) train an LSTM-based language model to generate shareable clinical notes us-ing differential privacy (Dwork et al., 2006).”
Local Differential Privacy-Based Federated Learning under Personalized Settings
Wu, X., Xu, L., & Zhu, L. (2023) · Applied Sciences · doi:10.3390/app13074168 · Cited by 18
Federated learning with superquantile aggregation for heterogeneous data
Pillutla, K., Laguel, Y., Malick, J., & Harchaoui, Z. (2023) · Machine Learning · doi:10.1007/s10994-023-06332-x · Cited by 31
“Differential privacy was introduced in [31, 30] to formalize the loss of privacy of an individual user in releasing population-level aggregates.”
BackgroundDistributed Differential Privacy via Shuffling Versus Aggregation: A Curious Study
Wei, Y. X., Jia, J., Wu, Y., Hu, C., Dong, C., Liu, Z., Chen, X., Peng, Y., & Wang, S. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3351474 · Cited by 24
“What inspired the study we present in this paper is the observation that the architecture of the shuffle model resembles that of private aggregation [17], [18], [19], [20], which has already been studied for more than a decade.”
BackgroundComprehensive Review of Privacy, Utility, and Fairness Offered by Synthetic Data
Kiran, A., Rubini, P. E., & Kumar, S. S. (2025) · IEEE Access · doi:10.1109/access.2025.3532128 · Cited by 72
“Differential Privacy (DP) [11] introduced by Dwork which used the concepts of additive noise and micro-aggregation [12], suggested that no real data need to be released for any work, instead only the statistical representation of the dataset is shared with no private information in the dataset.”
Computational Differential Privacy from Lattice-Based Cryptography
Valovich, F., & Aldà, F. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-76620-1_8 · Cited by 18
“The binomial mechanism from [15] and the Skel-lam mechanism introduced in this work serve these purposes.”
BackgroundMethodInfluentialCharacterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems.
Song, S., Thakkar, O. D., & Thakurta, A. (2020) · Cited by 25
Differentially Private Clustering via Maximum Coverage
Jones, M., Nguyễn, H. L., & Nguyen, T. (2021) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v35i13.17375 · Cited by 18
Privacy pitfalls of releasing in-vehicle network data
Gazdag, A., Lestyán, S., Remeli, M., Ács, G., Holczer, T., & Biczók, G. (2022) · Vehicular Communications · doi:10.1016/j.vehcom.2022.100565 · Cited by 18
“2 does not release any information that is specific to any single record in dataset D up to ε and δ, where δ is preferably smaller than 1/|D| [48].”
BackgroundPRIVIC: A privacy-preserving method for incremental collection of location data
Biswas, S., & Palamidessi, C. (2023) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2024-0033 · Cited by 25
“[2], a mathematical property that makes it difficult for an attacker to detect the presence of a record in a dataset.”
BackgroundA Practical Application of Differential Privacy to Personalized Online Advertising.
Lindell, Y., & Omri, E. (2011) · Cited by 18
Distributed Private Data Analysis: Lower Bounds and Practical Constructions
Shi, E., Chan, T.-H. H., Rieffel, E. G., & Song, D. X. (2017) · ACM Transactions on Algorithms · doi:10.1145/3146549 · Cited by 18
“One natural idea for achieving this is to have the parties rely on generic multi-party computation (MPC) to “realize” the trusted curator that implements a differentially private mechanism [1, 16].”
BackgroundResultInfluentialPrivacy-preserving data sharing via probabilistic modeling
Jälkö, J., Lagerspetz, E., Haukka, J. K., Tarkoma, S., Honkela, A., & Samuel Kaski, A. (2021) · Patterns · doi:10.1016/j.patter.2021.100271 · Cited by 18
“We compared the data sharing method against perturbing covariance matrix with Gaussian noise, according to the Gaussian mechanism [11], called “tailored mechanism” here.”
BackgroundMethodPrivacy Preserving Stream Analytics: The Marriage of Randomized Response and Approximate ComputingPreprint
Quoc, D. L., Beck, M., Bhatotia, P., Chen, R., Fetzer, C. W., & Strufe, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.05403 · Cited by 19
“Examples include Privad [49], PDDP [27], DJoin [75], SplitX [26], πBox [65], KISS [92], Koi [50], xBook [89], Popcorn [52], and many other systems [13, 34, 55].”
BackgroundPrivacy-Preserving Causal Inference via Inverse Probability WeightingPreprint
Lee, S. K., Gresele, L., Park, M., & Muandet, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12592 · Cited by 20
Differentially Private Real-Time Release of Sequential Data
Zhang, X., Khalili, M. M., & Liu, M. (2022) · ACM Transactions on Privacy and Security · doi:10.1145/3544837 · Cited by 25
“Toward this end, differential privacy [Dwork 2006] has been widely used to provide a strong privacy guarantee; it is generally achieved by disclosing a noisy version of the underlying data so that changes in the data can be effectively obscured.”
BackgroundResultInfluentialCollusion Resistant Federated Learning with Oblivious Distributed Differential Privacy
Byrd, D., Mugunthan, V., Polychroniadou, A., & Balch, T. R. (2022) · ACM International Conference on AI in Finance (ICAIF) · doi:10.1145/3533271.3561754 · Cited by 19
Federated Synthetic Data Generation with Stronger Security Guarantees
Ghavamipour, A. R., Türkmen, F., Wang, R., & Liang, K. (2023) · ACM Symposium on Access Control Models and Technologies (SACMAT) · doi:10.1145/3589608.3593835 · Cited by 17
DProvDB: Differentially Private Query Processing with Multi-Analyst Provenance
Zhang, S., & He, X. (2023) · Proceedings of the ACM on Management of Data · doi:10.1145/3626761 · Cited by 17
“This setting is common to see in the multi-party computation research community [18] (a.”
BackgroundSiren+: Robust Federated Learning With Proactive Alarming and Differential Privacy
Guo, H., Wang, H., Song, T., Yang, H., Ma, R., Jin, X., Xue, Z., & Guan, H. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3362534 · Cited by 27
“A widely used method to protect data privacy is differential privacy [55], which sets up a standard to measure the privacy guarantee of a randomized algorithm.”
MethodVakili, T., Henriksson, A., & Dalianis, H. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02546-8 · Cited by 24
“As it is typically formulated, we have (ǫ , δ) -differential privacy [33] for an aggregation M with range R if Differential privacy has also been adapted for deep learning.”
BackgroundA differential privacy aided DeepFed intrusion detection system for IoT applications
Anwar, S. S., Asaduzzaman, A., & Sarker, I. H. (2024) · Security and Privacy · doi:10.1002/spy2.445 · Cited by 18
“The suggested study strategy makes use of the variation developed in Reference 32 to account for the possibility that plain-differential privacy may be compromised with probability (preferably, less than 1/ | D | ).”
DStress: Efficient Differentially Private Computations on Distributed Data
Papadimitriou, A., Narayan, A., & Haeberlen, A. (2017) · European Conference on Computer Systems · doi:10.1145/3064176.3064218 · Cited by 22
Decentralized Detection With Robust Information Privacy Protection
Sun, M., & Tay, W. P. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2916650 · Cited by 21
“The papers [37], [39]–[43] propose methods to achieve (local) differential privacy, while the works [31], [44]–[46] investigate privacy-preserving distributed data analytics.”
MethodPrivacy and Policy in Polystores: A Data Management Research Agenda
Kroll, J. A., Kohli, N., & Laskowski, P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33752-0_5 · Cited by 22
Collaborative Deep Learning for Medical Image Analysis with Differential Privacy
Yuan, D., Zhu, X., Wei, M., & Ma, J. (2019) · Globecom · doi:10.1109/globecom38437.2019.9014259 · Cited by 20
“The mechanisms of differential privacy mainly include the Laplace mechanism [17], the exponential mechanism [18] and the Gaussian mechanism [19].”
BackgroundSocial-Aware Privacy-Preserving Mechanism for Correlated Data
Liao, G., Chen, X., & Huang, J. (2020) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2020.2994213 · Cited by 17
Mohammady, M., Xie, S., Hong, Y., Zhang, M., Wang, L., Pourzandi, M., & Debbabi, M. (2020) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3372297.3417259 · Cited by 22
“…Privacy. ad-vantagesinnumerousapplications,thedefinitionof ( ϵ , δ )-differential First, ( ϵ , δ ) -differential privacy was applied to the analysis of the by ϵ -differential privacy), a single Gaussian mechanism satisfies a curve of ( ϵ ( δ ) , δ ) -differential privacy definitions [21].”
MethodLam-Weil, J., Laurent, B., & Loubes, J. (2021) · Bernoulli · doi:10.3150/21-bej1358 · Cited by 40
“Differential privacy as expressed in [25, 24] is the most common formalization of the problem of privacy.”
BackgroundPART-GAN: Privacy-Preserving Time-Series Sharing
Wang, S., Rudolph, C., Nepal, ., Grobler, M. M., & Chen, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61609-0_46 · Cited by 17
Improving Laplace Mechanism of Differential Privacy by Personalized Sampling
Huang, W. C., Zhou, S., Zhu, T., Liao, Y., Wu, C., & Qiu, S. (2020) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom50675.2020.00088 · Cited by 17
“In order to improve the accuracy, Dwork et al. [5] relaxed the differential privacy by introduction of δ -approximate differential privacy.”
BackgroundNonparametric Differentially Private Confidence Intervals for the Median
Drechsler, J., Globus-Harris, I., McMillan, A., Sarathy, J., & Smith, A. (2022) · Journal of Survey Statistics and Methodology · doi:10.1093/jssam/smac021 · Cited by 17
Differentially Private Learning with Grouped Gradient Clipping
Liu, H., Li, C., Liu, B., Wang, P., Ge, S., & Wang, W. (2021) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3469877.3490594 · Cited by 21
“Differential privacy mechanism [8, 9] provides a feasible way to train privacy-preserving models.”
BackgroundPANDA: Lightweight non-interactive privacy-preserving data aggregation for constrained devices
Wang, M., He, K., Chen, J., Du, R., Zhang, B., & Li, Z. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.01.007 · Cited by 20
Wang, C., Bater, J., Nayak, K., & Machanavajjhala, A. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3526151 · Cited by 17
“To this end, inspired by the idea in [29], we implement a joint noise generation approach (Alg 2:46), where each server generates a random value zi ∈ Z232 uniformly at random and contributes it as an input to sDPTimer.”
MethodBayes Security: A Not So Average Metric
Konstantinos Chatzikokolakis, A., Cherubin, G., Catuscia Palamidessi, A., & Troncoso, C. (2023) · IEEE Computer Security Foundations Workshop (CSFW) · doi:10.1109/csf57540.2023.00011 · Cited by 17
“One may consider ( ε, δ ) -LDP [15].”
Differential Privacy in Practice
Shoaran, M., Thomo, A., & Weber, J. H. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32873-2_2 · Cited by 17
“([4]) A sequence of m computations over a database D, each providing εi-DP, satisfies ( ∑ i εi)-DP.”
BackgroundPrivacy Amplification of Iterative Algorithms via Contraction Coefficients
Asoodeh, S., Díaz, M., & Calmon, F. P. (2020) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit44484.2020.9174133 · Cited by 28
“Differential privacy (DP) [1, 2] has become the standard definition for designing privacy-preserving machine learning algorithms.”
BackgroundAn Overview of De-Identification Techniques and Their Standardization Directions
Youm, H. Y. (2020) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2019ici0002 · Cited by 21
“T-closeness [7], [39] is an enhancement to L-diversity for datasets with attributes that are unevenly distributed, belong to a small range of values, or are categorical.”
BackgroundSplitX: high-performance private analytics
Chen, R., Akkuş, İ. E., & Francis, P. (2013) · ACM SIGCOMM Computer Communication Review · doi:10.1145/2534169.2486013 · Cited by 17
Flood, M. D., Katz, J. I., Ong, S. J., & Smith, A. (2013) · SSRN Electronic Journal · doi:10.2139/ssrn.2320795 · Cited by 17
“, At are run on overlapping datasets, then their joint output is (at most) t differentially private [59].”
BackgroundPrivacy-preserving Transfer Learning for Knowledge Sharing.Preprint
Guo, X., Yao, Q., Tu, W.-W., Chen, Y., Dai, W., & Yang, Q. (2018) · arXiv (Cornell University) · Cited by 35
Differentially Private Clustering: Tight Approximation RatiosPreprint
Ghazi, B., Kumar, R., & Manurangsi, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.08007 · Cited by 60
“6 Definition 2 (Differential Privacy (DP) [DMNS06, DKM + 06]) .”
BackgroundPrivate and polynomial time algorithms for learning Gaussians and beyondPreprint
Ashtiani, H., & Liaw, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.11320 · Cited by 17
“learning Gaussians under the approximate (ε, δ)-differential privacy model [14] (or approximate-DP for short).”
BackgroundZhang, L., Wang, X., Wang, J., Pung, R., Wang, H., & Lam, K. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3348122 · Cited by 19
“More precisely, we say that a (randomized) algorithm M is -DP [23], with a parameter (cid:7) which is called privacy budget, if and only if: for any two data sets D , D which only differ in one data record, and for any possible outcome set S ⊆ Range ( M ) , we have”
BackgroundOn Data Distribution Leakage in Cross-Silo Federated Learning
Jiang, Y., Luo, X., Wu, Y., Zhu, X., Xiao, X., & Ooi, B. C. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3349323 · Cited by 20
“Formally, differential privacy is defined as follows: Definition 1 (Differential Privacy [24]): A randomized al-gorithm A satisfies ( (cid:3), δ ) -differential privacy, if for any two neighboring datasets D, D differing in only one record and for any set of outputs O ⊆ Range ( A ) it holds that The…”
BackgroundA Federated Learning Framework Based on Differentially Private Continuous Data Release
Cai, J., Liu, X., Ye, Q., Liu, Y., & Wang, Y. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3364060 · Cited by 17
“Against the above attacks, DP, proposed by Dwork et al. [11], provides comprehensive theories to protect individual privacy.”
BackgroundInfluentialPLASMA: Private, Lightweight Aggregated Statistics against Malicious Adversaries
Mouris, D., Sarkar, P., & Tsoutsos, N. G. (2024) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2024-0064 · Cited by 16
A Quantitative Probabilistic Relational Hoare Logic
Avanzini, M., Barthe, G., Davoli, D., & Grégoire, B. (2025) · Proceedings of the ACM on Programming Languages · doi:10.1145/3704876 · Cited by 20
“Definition 5.7 (Differential privacy [Dwork et al. 2006a]).”
InfluentialOn the relation between identifiability, differential privacy, and mutual-information privacy
Wang, W., Ying, L., & Zhang, J. (2014) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2014.7028576 · Cited by 16
“A privacy–distortion pair ( ,D) is said to be achievable if there exists a mechanism M with output Y such that M satisfies -privacy level and E[d(X,Y )] ≤ D.”
BackgroundA Solution for Privacy Protection in MapReduce
Tran, Q. K., & Satō, H. (2012) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac.2012.70 · Cited by 17
“Formally, a computation F satisfies (ε, σ)-differential privacy [6] (where ε and σ are privacy parameters) if, for all datasets D and D’ whose only difference is a single item which is present in D but not D’, and for all outputs S ⊆ Range(F).”
BackgroundOn the Meaning and Limits of Empirical Differential Privacy
Charest, A.-S., & Hou, Y. T. (2017) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.v7i3.406 · Cited by 16
“Differential privacy (DP) was introduced as a measure of confidentiality protection by Dwork et al. (2006b) and Dwork (2006).”
BackgroundLyu, L. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207618 · Cited by 16
“the same mechanism run at each party (typically with less noise) necessitates mechanisms with stable distributions (like Gaussian distribution, Binomial distribution)—to guarantee proper calibration of known end-to-end response distribution— and cryptography for hiding all but the final result from participants, as ev…”
BackgroundA Survey on Statistical, Information, and Estimation—Theoretic Views on Privacy
Hsu, H., Gil, N. M., Bertrán, M., Sapiro, G., & Calmon, F. P. (2021) · IEEE BITS the Information Theory Magazine · doi:10.1109/mbits.2021.3108124 · Cited by 22
Secure Sublinear Time Differentially Private Median Computation
Böhler, J., & Kerschbaum, F. (2020) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2020.24150 · Cited by 27
“Secure Computation and DP: Dwork et al. [19] first mentioned that differential privacy combines well with secure computation.”
BackgroundMethodLuyen, N. V., Tuan, A. H., Duy, P. T., Vo, K. T., & Pham, V.-H. (2022) · International Symposium on Information and Communication Technology · doi:10.1145/3568562.3568665 · Cited by 20
“In the study [9], the author demonstrated that privacy in the implementation of FL would be strongly protected when applying DP.”
BackgroundDifferential initial-value privacy and observability of linear dynamical systems
Wang, L., Manchester, I. R., Trumpf, J., & Shi, G. (2022) · Automatica · doi:10.1016/j.automatica.2022.110722 · Cited by 16
“(a) follows the standard differential privacy [23, 39] and has been studied in [13,30].”
BackgroundStochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design
Sun, Y., Shao, J., Mao, Y., Li, S., & Zhang, J. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3334732 · Cited by 16
“Compared with original DP definitions [37], [38], MI-DP is often considered to be more intuitive, because it explicitly incorporates the well-established concept of mutual information.”
MethodDesign of policy-aware differentially private algorithms
Haney, S., Machanavajjhala, A., & Ding, B. (2015) · Proceedings of the VLDB Endowment · doi:10.14778/2856318.2856322 · Cited by 16
APDP: Attack-Proof Personalized Differential Privacy Model for a Smart Home
Zhang, Y., Qu, Y., Gao, L., Luan, T. H., Zheng, X., Chen, S., & Xiang, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2953133 · Cited by 20
“Under the framework of differential privacy, numerous mechanisms have been proposed to achieve privacy preservation, e.g., Laplace noise [18] and sampling [19].”
BackgroundMethodAn Efficient Data Aggregation Scheme with Local Differential Privacy in Smart Grid
Gai, N., Xue, K., He, P., Zhu, B., Liu, J., & He, D. (2020) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn50589.2020.00027 · Cited by 16
“An exem-plary realization of this technique is through Differential Privacy (DP) [17,18].”
MethodDREAM: DiffeRentially privatE smArt MeteringPreprint
Ács, G., & Castelluccia, C. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1201.2531 · Cited by 16
“Although [6] describes protocols for generating shares of random noise which is secure against malicious participants, it requires communication between users and it uses expensive secret sharing techniques resulting in high overhead in case of large number of users.”
BackgroundUsable Differential Privacy: A Case Study with PSIPreprint
Murtagh, J., Taylor, K., Kellaris, G., & Vadhan, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.04103 · Cited by 17
“Differential privacy [5, 4] is an attractive approach to preserving privacy while maintaining utility for statistical analysis.”
BackgroundThe Complexity of Verifying Loop-Free Programs as Differentially Private
Gaboardi, M., Kobbi Nissim, B., & Purser, D. (2019) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.icalp.2020.129 · Cited by 17
“Definition 6 (Differential Privacy [22, 21]) .”
Private Stochastic Convex Optimization: Optimal Rates in $\ell_1$ GeometryPreprint
Asi, H., Feldman, V., Koren, T., & Talwar, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.01516 · Cited by 16
Covariance-Aware Private Mean Estimation Without Private Covariance EstimationPreprint
Brown, G., Gaboardi, M., Smith, A., Ullman, J., & Zakynthinou, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.13329 · Cited by 54
“(2)To simplify the discussion, we focus only on the ε parameter, although our results and many of those we discuss require relaxations of differential privacy such as approximate [28] or concentrated [26, 8] differential privacy, which have different parameterizations.”
ResultDifferentially Private Stochastic Optimization: New Results in Convex and Non-Convex SettingsPreprint
Bassily, R., Guzmán, C., & Menart, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.05585 · Cited by 16
“Differential Privacy [DKM + 06].”
Do I Get the Privacy I Need? Benchmarking Utility in Differential Privacy LibrariesPreprint
Garrido, G. M., Near, J. P., Aitsam, M., He, W., Matzutt, R., & Matthes, F. (2021) · SHURA (Sheffield Hallam University Research Archive) (Sheffield Hallam University) · doi:10.48550/arxiv.2109.10789 · Cited by 17
“DP is formally described in Definition 1, which is based on [37]: Definition 1 ( ( ε , δ )-Differential Privacy ).”
BackgroundPrivacy Preserving Time-Series Forecasting of User Health Data Streams
Imtiaz, S., Horchidan, S.-F., Abbas, Z., Arsalan, M., Chaudhry, H. N., & Vlassov, V. (2020) · 2020 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata50022.2020.9378186 · Cited by 15
“When an algorithm requires multiple additive noise mechanisms, the privacy guarantee follows from the basic composition theorem [16], [17] or from advanced composition theorems and their extensions [18]–[20].”
MethodAnalyzing Preference Data With Local Privacy: Optimal Utility and Enhanced Robustness
Wang, S., Luo, X., Qian, Y., Du, J., Lin, W., & Yang, W. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3207486 · Cited by 15
“…aggregation systems is data perturbation, which uses techniques of generalization (e.g., k -anonymity [34] in [35]) and randomization (e.g., Gaussian noise adding [36], randomized response [37] and differential privacy [5]) to hide the exact value of each user’s true data or the aggregated result.”
MethodImproved Differential Privacy Noise Mechanism in Quantum Machine Learning
Yang, H., Li, X., Liu, Z., & Pedrycz, W. (2023) · IEEE Access · doi:10.1109/access.2023.3274471 · Cited by 17
“Definition 2 (Loose Differential Privacy): [21] For a query mechanism M : D n → d provides ( ϵ, δ )-differential privacy if for adjacent datasets D , D ∈ D n , and any output S of M , This definition allows a small gap.”
BackgroundDifferential privacy protection method based on published trajectory cross-correlation constraint
Hu, Z., & Yang, J. (2020) · PLoS ONE · doi:10.1371/journal.pone.0237158 · Cited by 15
“proposed a differential privacy protection method to protect the leaking of private information by adding random disturbed noise to the data set [3,4].”
Evading the Curse of Dimensionality in Unconstrained Private GLMs
Song, S., Steinke, T., Thakkar, O. D., & Thakurta, A. (2021) · International Conference on Artificial Intelligence and Statistics · Cited by 82
Gao, J., Gong, R., & Yu, F.-Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i4.20315 · Cited by 15
Offset-Symmetric Gaussians for Differential Privacy
Sadeghi, P., & Korki, M. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3185770 · Cited by 15
“Definition 2: (Pure/Approximate Differential Privacy [3]) A randomized mechanism M : X n → Y is said to satisfy (ε, δ)-differential privacy or (ε, δ)-DP for short, if for all x, x ∈ X n differing on a single element and all events E ⊂ Y , we have”
BackgroundMethodInfluentialLiu, X., Wang, Y., Xiao, J., Chi, M., & Liu, Z. (2022) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2022.01.024 · Cited by 15
Hou, D., Zhang, J., Ma, J., Zhu, X., & Man, K. L. (2021) · International Symposium on Parallel Architectures, Algorithms and Programming · doi:10.1109/paap54281.2021.9720452 · Cited by 19
Network Shuffling: Privacy Amplification via Random Walks
Liew, S. P., Takahashi, T., Takagi, S., Kato, F., Cao, Y., & Yoshikawa, M. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3526162 · Cited by 23
“For this purpose, differential privacy (DP) [19, 20], which is widely regarded as a gold-standard notion of privacy, has seen adoption by companies such as Google [23], Apple [16], Linkedin [44] and Microsoft [17].”
BackgroundPrivate Numbers in Public Policy: Census, Differential Privacy, and Redistricting
Cohen, A., Duchin, M., Matthews, J., & Suwal, B. (2022) · Harvard Data Science Review · doi:10.1162/99608f92.22fd8a0e · Cited by 15
In Search of Lost Utility: Private Location Data
Lestyán, S., Ács, G., & Biczók, G. (2022) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2022-0076 · Cited by 17
“Definition 3.1 ( ( (cid:15), δ ) -Differential Privacy [15]) .”
BackgroundInfluentialCombining Differential Privacy and PIR for Efficient Strong Location Privacy
Fung, E., Kellaris, G., & Papadias, D. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22363-6_16 · Cited by 23
“In order to avoid this type of privacy breaches, we employ the notion of ε-differential privacy [8].”
MethodKnowledge-oriented secure multiparty computation
Mardziel, P., Hicks, M., Katz, J. I., & Srivatsa, M. (2012) · ACM Workshop on Programming Languages and Analysis for Security · doi:10.1145/2336717.2336719 · Cited by 15
“[4] show that if f is a differentially private function, then the process of running an SMC protocol that computes f is also differentially private (at least in a computational sense).”
BackgroundPrivacy-preserving MaaS fleet management
Belletti, F., & Bayen, A. M. (2017) · Transportation research procedia · doi:10.1016/j.trpro.2017.05.055 · Cited by 15
Preliminary of Differential Privacy
Zhu, T., Li, G., Zhou, W., & Yu, P. S. (2017) · Advances in information security · doi:10.1007/978-3-319-62004-6_2 · Cited by 15
LightDP: towards automating differential privacy proofs
Zhang, D., & Kifer, D. (2017) · ACM SIGPLAN Notices · doi:10.1145/3093333.3009884 · Cited by 15
The Cost of Privacy in Asynchronous Differentially-Private Machine Learning
Farokhi, F., Wu, N., Smith, D. B., & Kâafar, M. A. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3050603 · Cited by 15
“The composition bounds stem from the relationship between Rényi differential privacy [5] and approximate differential privacy [6].”
BackgroundA Locality Sensitive Hashing Based Approach for Federated Recommender System
Hu, H., Dobbie, G., Salcic, Z. A., Liu, M., Zhang, J., & Zhang, X. (2020) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid49817.2020.000-1 · Cited by 15
“A better alternative is to make use of differential privacy to control the trade-off between data utility and privacy, since differential privacy has a solid theoretical foundation and strong privacy protection capability [6].”
BackgroundMethodDifferential Privacy Images Protection Based on Generative Adversarial Network
Ren, Y., Ma, X., Bai, X., & Su, X. (2020) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom50675.2020.00232 · Cited by 15
“Definition 1: ( (ε, δ) -Differential Privacy[17]): If a random algorithm A satisfies ((cid:2013), (cid:2012)) -differential privacy, for all inputs (cid:1856), (cid:1856) (cid:4593) differing in at most one user’s one attribute value, and for all sets of possible outputs ∈ ((cid:1827))(cid:3439) ,…”
BackgroundRandom Projections, Graph Sparsification, and Differential Privacy
Upadhyay, J. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-42033-7_15 · Cited by 15
Distributed Sketching Methods for Privacy Preserving RegressionPreprint
Bartan, B., & Pilancı, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.06538 · Cited by 15
“We use the notion of differential privacy given in Definition 1 [5].”
MethodPrivacy-Preserving Aggregation of Smart Metering via Transformation and Encryption
Lyu, L., Law, Y. W., Jin, J., & Palaniswami, M. S. (2017) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom/bigdatase/icess.2017.273 · Cited by 14
“[15] proposed the protocol called “Our Data, Ourselves” (ODO) for achieving distributed differential privacy.”
BackgroundMethodInfluentialAdvancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond
Galli, F., Jung, K., Biswas, S., Palamidessi, C., & Cucinotta, T. (2023) · SN Computer Science · doi:10.1007/s42979-023-02292-0 · Cited by 22
Edge-DPSDG: An Edge-Based Differential Privacy Protection Model for Smart Healthcare
Lyu, M., Ni, Z., Chen, Q., & Li, F. (2024) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2024.3366071 · Cited by 17
“(( (cid:2), δ )-DifferentialPrivacy[65]): Arandomized mechanism M gives ( (cid:2), δ )-differential privacy for all set of outputs S , S ⊂ Range ( M ) , and for any adjacent datasets of D and D , D can be obtained from D by removing or adding one single record, if M satisfies: For a particular query…”
Christodoulou, P., & Limniotis, K. (2024) · Network · doi:10.3390/network4010005 · Cited by 15
“Therefore, we have the following definition based on the variant introduced by [62]: Definition 1.”
On Differentially Private Gaussian Hypothesis Testing
Degue, K. H., & Ny, J. L. (2018) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2018.8635911 · Cited by 14
“[20], [21] Let q : H → R be a query.”
BackgroundMethodAn optimal (∊,δ) -differentially private learning of distributed deep fuzzy models
Kumar, M., Rossbory, M., Moser, B., & Freudenthaler, B. (2020) · Information Sciences · doi:10.1016/j.ins.2020.07.044 · Cited by 14
Metadata
- Authors
- Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., & Naor, M.
- Affiliations
- Microsoft (United States) (US)
- Stanford University (US)
- Weizmann Institute of Science (IL)
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Pages
- 486-503
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1557833142
- Cited by
- 1,835
- References
- 31
- Citations by year
- 2026: 65 · 2025: 138 · 2024: 184 · 2023: 179 · 2022: 175 · 2021: 188 · 2020: 216 · 2019: 123 · 2018: 80 · 2017: 81 · 2016: 61 · 2015: 69 · 2014: 78 · 2013: 70 · 2012: 52
- FWCI
- 7.51
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Lecture notes in computer science (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Keywords
- malicious security, verifiable secret sharing, Gaussian noise, exponential distribution, random bit generation, distributed protocols
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.