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 801–900 of 1,008
On the Round Complexity of the Shuffle Model
Beimel, A., Haitner, I., Kobbi Nissim, B., & Stemmer, U. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64378-2_24 · Cited by 19
Learning and Evaluating a Differentially Private Pre-trained Language Model
Hoory, S., Feder, A., Tendler, A., Cohen, A., Erell, S., Laish, I., Nakhost, H., Stemmer, U., Benjamini, A., Hassidim, A., et al. (2021) · Workshop on Privacy in Natural Language Processing (PrivateNLP) · doi:10.18653/v1/2021.privatenlp-1.3 · Cited by 14
“Differential Privacy (DP; Dwork et al., 2006; Dwork, 2011; Dwork et al., 2014) is a framework that quantifies the privacy leaked by some randomized algorithm accessing a private dataset, reader unfamiliar with DP, can consult the short introduction in Appendix A.”
BackgroundInfluentialPrivacy-Preserving Mechanisms for Multi-Label Image Recognition
Xu, H., Cai, Z., & Li, W. (2022) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3491231 · Cited by 17
Towards Verifiable Differentially-Private Polling
Garrido, G. M., Sedlmeir, J., & Babel, M. (2022) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3538969.3538992 · Cited by 15
“[12], as the distribution in the range [l ,u] is exponential, we maintain the same privacy guarantee by increasing the probability of not adding noise by a trivial amount (i.”
BackgroundMethodInfluentialSelective MPC: Distributed Computation of Differentially Private Key-Value Statistics
Humphries, T., Mahdavi, R. A., Veitch, S., & Kerschbaum, F. (2022) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3548606.3560559 · Cited by 18
“[17] provided protocols to generate Gaussian and exponentially distributed noise in a distributed setting.”
BackgroundA Differential Privacy Protection Protocol Based on Location Entropy
Guo, P., Ye, B., Chen, Y., Li, T., Yang, Y., Qian, X., & Yu, X. (2022) · Tsinghua Science & Technology · doi:10.26599/tst.2022.9010003 · Cited by 14
Frequency Estimation Mechanisms Under ϵδ-Utility-Optimized Local Differential Privacy
Zhang, Y., Zhu, Y., Zhou, Y., & Yuan, J. (2023) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2023.3238839 · Cited by 14
“The most common method to achieve it is to add Gaussian noise [13], [14], which is always applied to mean estimation.”
MethodUnifying Privacy Measures via Maximal (α, β)-Leakage (MαbeL)
Gilani, A., Kurri, G. R., Kosut, O., & Sankar, L. (2024) · IEEE Transactions on Information Theory · doi:10.1109/tit.2024.3384922 · Cited by 18
“Approximate differential privacy is proposed as a relaxation of DP to allow data releases with higher utility [45].”
BackgroundPrivacy-Aware Document Visual Question Answering
Tito, R., Nguyen, K., Tobaben, M., Kerkouche, R., Souibgui, M. A., Jung, K., Jälkö, J., d’Andecy, V. P., Joseph, A., Kang, L., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70552-6_12 · Cited by 28
Differentially Private Stream Processing at Scale
Zhang, B., Doroshenko, V., Kairouz, P., Steinke, T., Thakurta, A., Ma, Z., Cohen, E., Apte, H., & Spacek, J. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3685800.3685833 · Cited by 17
Differentially Private Neural Tangent Kernels (DP-NTK) for Privacy-Preserving Data Generation
Yang, Y., Adamczewski, K., Li, X., Sutherland, D. J., & Park, M. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15985 · Cited by 17
Query optimization for differentially private data management systems
Peng, S., Yang, Y., Zhang, Z., Winslett, M., & Yu, Y. H. (2013) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2013.6544900 · Cited by 14
“, ( ,δ)-DP [5], which guarantees -DP with a certain probability.”
BackgroundRR-LADP: A Privacy-Enhanced Federated Learning Scheme for Internet of Everything
Li, Z., Tian, Y., Zhang, W., Liao, Q., Liu, Y., Du, X., & Guizani, M. (2021) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2021.3059958 · Cited by 14
Stochastic Adaptive Line Search for Differentially Private Optimization
Chen, C., & Lee, J.-W. (2020) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata50022.2020.9378011 · Cited by 14
“applying a naive additive privacy composition lemma [28]) would result in ( 1 + max it · 2, 0)-DP.”
MethodDifferential privacy with δ-neighbourhood for spatial and dynamic datasets
Fang, C., & Chang, E. (2014) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/2590296.2590320 · Cited by 14
“For example, ( , δ)-differential privacy [5] relaxes the bound with an additive factor δ, and ( , τ)-probabilistic differential privacy [17] allows the bound to be violated with a probability τ .”
BackgroundVTDP: Privately Sanitizing Fine-grained Vehicle Trajectory Data with Boosted Utility
Liu, B., Xie, S., Wang, H., Hong, Y., Ban, X. J., & Mohammady, M. (2019) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2019.2960336 · Cited by 14
Kobbi Nissim, B. (2008) · The Kluwer international series on advances in database systems · doi:10.1007/978-0-387-70992-5_16 · Cited by 14
“This is a very different notion of privacy from what we seek herein – in general there is no guarantee that the outcome of the datamining analysis procedure itself preserves individual privacy.”
BackgroundNon-Interactive Differential Privacy: a SurveyPreprint
Leoni, D. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1205.2726 · Cited by 14
Information-theoretic metrics for Local Differential Privacy protocolsPreprint
Lopuhaä-Zwakenberg, M., Škorić, B., & Li, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.07826 · Cited by 16
“However, in practice it can be difficult to fulfill such a stringent definition of privacy [35, 26, 25], and for this reason many relaxations of ε -(L)DP have been introduced [22, 14, 20, 42].”
BackgroundLiu, F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.08554 · Cited by 14
“There also exist softer versions to the pure -DP that include the ( , δ)-approximate differential privacy (aDP) [25], the ( , δ)-probabilistic DP (pDP) [26], the ( , δ) random differential privacy (rDP) [27], and the ( , τ)-concentrated differential privacy (cDP) [28].”
BackgroundLearning from Mixtures of Private and Public PopulationsPreprint
Bassily, R., Moran, S., & Nandi, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.00331 · Cited by 14
Differentially Private Histograms under Continual Observation: Streaming Selection into the UnknownPreprint
Cardoso, A. R., & Rogers, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16787 · Cited by 14
“We will refer to as the privacy loss parameter in the definition of DP. Definition 2.1 (Dwork et al. (2006b), Dwork et al. (2006a)).”
BackgroundMethodInfluentialLocally Private k-Means in One RoundPreprint
Chang, A., Ghazi, B., Kumar, R., & Manurangsi, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.09734 · Cited by 14
“Recently, differential privacy (DP) (Dwork et al., 2006b,a) has emerged as a popular definition, due to its mathematical rigor and strong guarantees.”
BackgroundDifferentiaalisesti yksityinen approksimatiivinen Bayes-päättely todennäköisyysmalleille
Jälkö, J. (2023) · Aaltodoc (Aalto University) · Cited by 14
Test & Evaluation Best Practices for Machine Learning-Enabled SystemsPreprint
Chandrasekaran, J., Cody, T., McCarthy, N., Lanus, E., & Freeman, L. E. B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4862589 · Cited by 14
Composition Theorems for Interactive Differential Privacy
Lyu, X. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-0705 · Cited by 13
Securely Sampling Discrete Gaussian Noise for Multi-Party Differential Privacy
Wei, C., Yu, R., Fan, Y., Chen, W., & Wang, T. (2023) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3576915.3616641 · Cited by 23
Privacy-Enhancing Person Re-identification Framework – A Dual-Stage Approach
Kansal, K., Wong, Y., & Kankanhalli, M. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00835 · Cited by 22
“[11] and is to first derive the frequency distribution of the tuples in the input data and then publish a noisy version of the distribution to preserve privacy.”
BackgroundBenchmarking Secure Sampling Protocols for Differential Privacy
Fu, Y., & Wang, T. (2024) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3658644.3690257 · Cited by 13
“In fact, existing works [14] using continuous noise in MPC did not formally quantify additional statistical distance.”
InfluentialMuthukrishnan, G., & Kalyani, S. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3536277 · Cited by 13
“The Gaussian mechanism that adds i.i.d. noise from Gaussian distribution is a popular mechanism that has been studied extensively [1], [7], [8], [9], [10]; the Laplace mechanism is another popular mechanism that, unlike Gaussian, can ensure the stronger notion of DP with δ = 0.”
CropsDisNet: An AI-Based Platform for Disease Detection and Advancing On-Farm Privacy Solutions
Khan, M. B., Tamkin, S., Ara, J., Alam, M. M., & Bhuiyan, H. (2025) · Data · doi:10.3390/data10020025 · Cited by 13
A verifiable scheme for differential privacy based on zero-knowledge proofs
Wei, J., Chen, Y., Yang, X., Luo, Y. B., & Pei, X. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00028-z · Cited by 13
Private Similarity Computation in Distributed Systems: From Cryptography to Differential Privacy
Alaggan, M., Gambs, S., & Kermarrec, A.-M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25873-2_25 · Cited by 13
“Distributed noise generation has been addressed in the context of the secure multi-party and differential privacy [10].”
BackgroundIncreasing user controllability on device specific privacy in the Internet of Things
Asif, W., Rajarajan, M., & Lestas, M. (2017) · Computer Communications · doi:10.1016/j.comcom.2017.11.009 · Cited by 13
“(( (cid:15) , δ )-Differential Privacy (DP) [33]).”
ADAM-DPGAN: a differential private mechanism for generative adversarial network
Azadmanesh, M., Ghahfarokhi, B. S., & Talouki, M. A. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03902-9 · Cited by 13
Luo, Z., Amayri, M., Fan, W., & Bouguila, N. (2023) · Applied Intelligence · doi:10.1007/s10489-022-04378-3 · Cited by 13
“Theorem 2 (Exponential Mechanism [29]) Given a range R , a dataset D , a function u , and a privacy parameter (cid:12) , the mechanism M E (x, u, R ) : D −→ R satisfies (cid:12) − DP if M E (x, u, R ) output an element r ∈ R with probability P r satisfies that: where u(x, r) is the utility function and (cid:2) u is se…”
BackgroundMethodInfluentialInvestigating the Visual Utility of Differentially Private Scatterplots
Panavas, L., Crnovrsanin, T., Adams, J. L., Ullman, J., Sarvghad, A., Tory, M. K., & Dunne, C. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3292391 · Cited by 17
“Data can be more safely shared through the use of differential privacy algorithms [13], which protect individual privacy while enabling the public’s ability to see aggregate patterns.”
BackgroundPrivacy-preserving release of aggregate dynamic models
Ny, J. L., & Pappas, G. J. (2013) · doi:10.1145/2461446.2461454 · Cited by 13
Aggregating privatized medical data for secure querying applications
Singh, K., & Batten, L. (2016) · Future Generation Computer Systems · doi:10.1016/j.future.2016.11.028 · Cited by 13
New algorithms for preserving differential privacy
Roth, A. (2010) · Cited by 13
Privacy-Preserving Outlier Detection for Data Streams
Böhler, J., Bernau, D., & Kerschbaum, F. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-61176-1_12 · Cited by 16
“Either by adapting the sensitivity [17], additional privacy loss [3], by distinguishing between groups with different privacy guarantees [11,14], or by relaxing the adversary [19,23].”
Enhancing frequent location privacy-preserving strategy based on geo-Indistinguishability
Luo, H., Zhang, H., Long, S., & Lin, Y. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10789-0 · Cited by 13
“When δ > 0, we use the term approximate differential privacy [13].”
MethodEvent-trigger Optimal Consensus for Multi-agent System Subject to Differential Privacy
Dong, T., Zhu, H., & Hu, W. (2021) · International Journal of Control Automation and Systems · doi:10.1007/s12555-020-0343-7 · Cited by 13
“Among these algorithms, differential privacy is widely concerned because it is easy to implement [17,18] by adding Laplace noise conformed to the proper distribution.”
BackgroundExploring privacy-enhancing technologies in the automotive value chain
Garrido, G. M., Schmidt, K., Harth-Kitzerow, C., Klepsch, J., Luckow, A., & Matthes, F. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671528 · Cited by 14
“Differential privacy (DP) Mathematically guarantees that the output of a dataset analysis is “essentially” identical, despite the presence or absence of an individual in the dataset [15], [34].”
BackgroundPrivacy in Crowdsourced Platforms
Kandappu, T., Friedman, A., Sivaraman, V., & Boreli, R. (2015) · Computer communications and networks · doi:10.1007/978-3-319-08470-1_4 · Cited by 19
Measuring the achievable error of query sets under differential privacyPreprint
Li, C., & Miklau, G. (2012) · arXiv (Cornell University) · Cited by 13
Upadhyay, J. (2016) · arXiv (Cornell University) · Cited by 13
Generalization for Adaptively-chosen Estimators via Stable MedianPreprint
Feldman, V., & Steinke, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.05069 · Cited by 43
Distributed Private Data Analysis: On Simultaneously Solving How and WhatPreprint
Beimel, A., Kobbi Nissim, B., & Omri, E. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.2626 · Cited by 14
Huang, Z., & Gong, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.07890 · Cited by 15
“In order to provide privacy guarantee against such attacks, we define our privacy model formally by the notion of differential privacy (Dwork et al., 2006b, 2014).”
MethodAn Accurate, Scalable and Verifiable Protocol for Federated Differentially Private AveragingPreprint
Sabater, C., Bellet, A., & Ramon, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07218 · Cited by 15
“per party MSE Verif Risks Central DP [36] O(1) O(1/n2) No Trusted curator Local DP [55] O(1) O(1/n) No Verifiable secret sharing [35] O(n) O(1/n2) Yes Secure agg.”
BackgroundMethodInfluentialOn the Sample Complexity of Privately Learning Unbounded High-Dimensional GaussiansPreprint
Aden-Ali, I., Ashtiani, H., & Kamath, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.09929 · Cited by 13
Local Differential Privacy Is Equivalent to Contraction of $E_γ$-DivergencePreprint
Asoodeh, S., Aliakbarpour, M., & Calmon, F. P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.01258 · Cited by 14
“DP has several variants, including approximate DP [2], Rényi DP [3], and others [4–7].”
BackgroundOutput Perturbation for Differentially Private Convex Optimization: Faster and More GeneralPreprint
Lowy, A. M., & Razaviyayn, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.04704 · Cited by 15
Privacy-Preserving Dynamic Personalized Pricing with Demand LearningPreprint
Chen, X., Simchi‐Levi, D., & Wang, Y. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3700474 · Cited by 13
Xiao, H., Wan, J., & Devadas, S. (2023) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3576915.3623142 · Cited by 12
“[14] Cynthia Dwork, Krishnaram Kenthapadi, Frank McSherry, Ilya Mironov, and Moni Naor.”
BackgroundDifferentially Private Ad Conversion Measurement
Delaney, J., Ghazi, B., Harrison, C., Ilvento, C., Kumar, R. D., Manurangsi, P., Pál, M., Prabhakar, K., & Raykova, M. (2024) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2024-0044 · Cited by 14
Total Variation Meets Differential Privacy
Ghazi, E., & Issa, I. (2024) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2024.3384083 · Cited by 16
“As such, researchers have developed relaxations and variations of differential privacy to yield better composition behaviour, e.g., approximate DP [2], Rényi-DP [3], concentrated-DP [4], Gaussian DP [5], etc.”
BackgroundCommunication-Efficient Secure Logistic Regression
Agarwal, A., Peceny, S., Raykova, M., Schoppmann, P., & Seth, K. (2024) · IEEE European Symposium on Security and Privacy · doi:10.1109/eurosp60621.2024.00031 · Cited by 13
Reconstruction Attacks on Aggressive Relaxations of Differential Privacy
Protivash, P., Durrell, J., Kifer, D., Ding, Z., & Zhang, D. (2024) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.871 · Cited by 12
Dynamic calibration of trust and trustworthiness in AI-enabled systems
Liebherr, M., Enkel, E., Law, E. L., Mousavi, M. R., Sammartino, M., & Sieberg, P. M. (2026) · International Journal on Software Tools for Technology Transfer · doi:10.1007/s10009-026-00840-6 · Cited by 17
Challenging Differential Privacy:The Case of Non-interactive Mechanisms
Balu, R., Furon, T., & Gambs, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11212-1_9 · Cited by 12
“A relaxed notion differential privacy called ( ǫ , δ )-differential privacy [14], can be seen as a probabilistic variant in which the guarantees of differential privacy hold with probability of 1 − δ .”
BackgroundHuang, W. C., Zhou, S., Zhu, T., & Liao, Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3089518 · Cited by 12
Eriguchi, R., Ichikawa, A., Kunihiro, N., & Nuida, K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-662-64322-8_13 · Cited by 12
Efficient Noise Generation Protocols for Differentially Private Multiparty Computation
Eriguchi, R., Ichikawa, A., Kunihiro, N., & Nuida, K. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3227568 · Cited by 16
“To deal with that problem, differentially private mechanisms [5], [6], [7] add noise drawn from an appropriate distribution to an exact calculation result and make the distributions of outputs for two “similar” inputs approximately the same.”
BackgroundMethodInfluentialPrivacy-preserving cloud-edge collaborative learning without trusted third-party coordinator
Yu, X., Tang, D., & Zhao, W. (2023) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-023-00394-x · Cited by 12
“Based on privacy protection methods like homomorphic encryption (HE) [12], secure multi-party computation (MPC) [13], and differential privacy (DP) [14], several privacy-preserving CLLR schemes have been proposed.”
MethodPrivacy-Preserving Domain Adaptation of Semantic Parsers
Mireshghallah, F., Su, Y., Hashimoto, T., Eisner, J. M., & Shin, R. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.271 · Cited by 18
Advances in Differential Privacy and Differentially Private Machine Learning
Das, S., & Mishra, S. (2024) · Springer tracts in electrical and electronics engineering · doi:10.1007/978-981-97-0407-1_7 · Cited by 13
“However, some tools like propose-test-release and amplification-via-subsampling are not supported by zCDP, which led Bun, Dwork et al[10] to introduce a relaxation on zCDP, called truncated CDP in 2018. while CDP demands that the privacy loss is at least as concentrated as a Gaussian, tCDP relaxes that demand to havin…”
BackgroundInfluentialEfficient and Privacy-Enhanced Federated Learning Based on Parameter Degradation
Li, W., Yu, P., Cheng, Y., Yan, J., & Zhang, Z. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3399659 · Cited by 13
“( ( (cid:2), δ ) -differential privacy, ( (cid:2), δ ) -DP) [42]: A randomization mechanism M satisfies ( (cid:2), δ ) -differential privacy ( (cid:2) > 0 , δ > 0 ) when and only when for any adjacent input datasets D and D and any possible set of output values R M , there is The relaxed…”
BackgroundWang, J., Chang, X., Mišić, J., Mišić, V. B., Li, L., & Yao, Y. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3405004 · Cited by 12
“The sparsification-based methods, including compression-based [30], sketch-based [17], [44], and sampling-based [14], [15], regenerate stochastic gradients independently by unbiased or biased estimates of true gradients.”
On Learning Cluster Coefficient of Private Networks
Wang, Y., Wu, X., Zhu, J., & Xiang, Y. (2012) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2012.71 · Cited by 12
Anonymizing bag-valued sparse data by semantic similarity-based clustering
Liu, J., & Wang, K. (2012) · Knowledge and Information Systems · doi:10.1007/s10115-012-0515-8 · Cited by 13
Differential privacy: an exploration of the privacy-utility landscape
Mir, D. J. (2013) · doi:10.7282/t3ft8j2z · Cited by 19
“Subsequently, differential privacy was developed as a notion of privacy over a series of papers [11, 31, 33].”
BackgroundSeparating Computational and Statistical Differential Privacy in the Client-Server Model
Bun, M., Chen, Y.-H., & Vadhan, S. (2016) · Lecture notes in computer science · doi:10.1007/978-3-662-53641-4_23 · Cited by 15
“The sequence of works [DKM + 06, BNO08, MPRV09] introduced a paradigm that enables two or more parties to take advantage of CDP, either to achieve better utility or reduced round complexity, when computing a joint function of their private inputs: The parties use a secure multi-party computation…”
MethodEncrypting wireless network traces to protect user privacy: A case study for smart campus
Zhang, L., Öksüz, Ö., Nazaryan, L., Yue, C., Wang, B., Kiayias, A., & Bamis, A. (2016) · IEEE International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) · doi:10.1109/wimob.2016.7763266 · Cited by 12
Asymmetric Distances for Approximate Differential Privacy
Chistikov, D. V., Murawski, A. S., & Purser, D. (2019) · Warwick Research Archive Portal (University of Warwick) · doi:10.4230/lipics.concur.2019.10 · Cited by 12
Online Decision Making with Local Differential Privacy
Han, Y., Liang, Z., Wang, Y., & Zhang, J. (2026) · Operations Research · doi:10.1287/opre.2024.0984 · Cited by 12
Towards a privacy protection-capable noise fingerprinting for numerically aggregated data
Hu, Y., Hu, A., Li, C., Li, P., & Zhang, C. (2022) · Computers & Security · doi:10.1016/j.cose.2022.102755 · Cited by 12
Differential Private Deep Learning Models for Analyzing Breast Cancer Omics Data
Islam, M. M., Mohammed, N., Wang, Y., & Hu, P. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.879607 · Cited by 14
“RDP is a natural relaxation form of ∈ -DP (10) while overcomes the limitation of relaxed ( ϵ , d )-DP (28).”
BackgroundMethodCohere: Managing Differential Privacy in Large Scale Systems
Küchler, N., Opel, E., Lycklama, H., Viand, A., & Hithnawi, A. (2024) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp54263.2024.00122 · Cited by 12
“Lastly, we assume that there is no (side-channel) leakage [55] beyond the intentional data releases.”
BackgroundA New Lower Bound of Privacy Budget for Distributed Differential Privacy
Lu, Z., & Shen, H. (2017) · International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) · doi:10.1109/pdcat.2017.00014 · Cited by 12
“[4], extended the traditional differential privacy into distributed scenarios by combining the techniques from SMC and differential privacy in different applications.”
BackgroundMethodUsing Differential Privacy to Efficiently Mitigate Side Channels in Distributed Analytics
Xu, M., Papadimitriou, A., Feldman, A. J., & Haeberlen, A. (2018) · European Workshop on System Security · doi:10.1145/3193111.3193115 · Cited by 12
“…queries q 1 and q 2 are ε 1 - and ε 2 -differentially private, respectively, then the combination q 1 · q 2 is ε 1 + ε 2 -differentially private [7, 8] Because of this, it is possible to associate each data set with a “privacy budget” ε max that represents the desired strength of the overall…”
BackgroundFree gap information from the differentially private sparse vector and noisy max mechanisms
Ding, Z., Wang, Y., Zhang, D., & Kifer, D. (2019) · Proceedings of the VLDB Endowment · doi:10.14778/3368289.3368295 · Cited by 12
Private Empirical Risk Minimization With Analytic Gaussian Mechanism for Healthcare System
Ding, J., Errapotu, S. M., Guo, Y., Zhang, H., Yuan, D., & Pan, M. (2020) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2020.2997732 · Cited by 14
Privacy-preserving chi-squared test of independence for small samples
Sei, Y., & Ohsuga, A. (2021) · BioData Mining · doi:10.1186/s13040-021-00238-x · Cited by 12
“Other methods for ( , δ)-differential privacy are proposed [49], which relaxes the -differential privacy as their privacy metric.”
MethodPrivacy Preservation in Social Network Data using Evolutionary Model
Srivatsan, S., & Maheswari, N. (2022) · Materials Today Proceedings · doi:10.1016/j.matpr.2022.03.251 · Cited by 12
The Optimal Mechanism in Differential Privacy: Multidimensional SettingPreprint
Geng, Q., & Viswanath, P. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.0655 · Cited by 12
“[12] introduce ( , δ)-differential privacy and show that adding random noise with Gaussian distribution can preserve ( , δ)-differential privacy for real-valued query function.”
BackgroundInformation, Privacy and Stability in Adaptive Data AnalysisPreprint
Smith, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.00820 · Cited by 14
“Definition 2 ([17, 16]) .”
Distributed Differentially Private Computation of Functions with Correlated NoisePreprint
Imtiaz, H., Mohammadi, J. A., & Sarwate, A. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.10059 · Cited by 12
“Our work is inspired by the seminal work of Dwork et al. [41] that proposed distributed noise generation for preserving privacy.”
MethodInfluentialPrivacy-preserving Q-Learning with Functional Noise in Continuous State SpacesPreprint
Wang, B., & Hegde, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.10634 · Cited by 13
“Differential privacy [DKM + 06, DMNS06] has developed into a strong standard for privacy guarantees in data analysis.”
BackgroundCrypt$ε$: Crypto-Assisted Differential Privacy on Untrusted ServersPreprint
Chowdhury, A. R., Wang, C., He, X., Machanavajjhala, A., & Jha, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.07756 · Cited by 30
“with the trust assumption of the CDP model is using cryptographic primitives [9, 14, 17, 20, 29, 31, 37, 41, 92, 93].”
MethodDesign of a Privacy-Preserving Data Platform for Collaboration Against Human TraffickingPreprint
Edge, D., Yang, W., Lytvynets, K., Cook, H., Galez-Davis, C., Darnton, H., & White, C. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.05688 · Cited by 12
“Under looser constraints, DPPro [67] uses random projections that maintain probabilistic (ε,δ )-differential privacy [17].”
MethodPrivately Answering Classification Queries in the Agnostic PAC ModelPreprint
Nandi, A., & Bassily, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.13553 · Cited by 23
A Members First Approach to Enabling LinkedIn's Labor Market Insights at ScalePreprint
Rogers, R., Cardoso, A. R., Mancuhan, K., Kaura, A., Gahlawat, N., Jain, N., Ko, P., & Ahammad, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13981 · Cited by 12
“Recall the definition of differential privacy [7, 6].”
An Uncertainty Principle is a Price of Privacy-Preserving MicrodataPreprint
Abowd, J. M., Ashmead, R., Cumings-Menon, R., Garfinkel, S., Kifer, D., Leclerc, P., Sexton, W., Simpson, A. E., Task, C., & ЖУРАВЛЕВ, П. В. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.13239 · Cited by 12
“We present such lower bound results for pure differential privacy [16], approximate differential privacy [15], and concentrated differential privacy [8], with nearly matching upper bounds.”
BackgroundSung, M., Cha, D., & Park, Y. R. (2021) · JMIR Medical Informatics · doi:10.2196/26914 · Cited by 12
“Differential privacy [11], which entails a semantic model, is another data privacy approach.”
BackgroundA Federated Learning-Based Light-Weight Privacy-Preserving Framework for Smart Healthcare Systems
Ramesh, V., Hariharasitaraman, S., Ganesh, S. S., B., P. N., & Hemalakshmi, G. R. (2022) · Advances in wireless technologies and telecommunication book series · doi:10.4018/978-1-7998-9636-4.ch019 · Cited by 12
DP-LTGAN: Differentially private trajectory publishing via Locally-aware Transformer-based GAN
Zhang, R., Ni, W., Fu, N., Hou, L., Zhang, D., & Zhang, Y. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.107686 · Cited by 14
Privacy-Preserving Multimodal Sentiment Analysis
Xu, H., Li, W., Takabi, D., Seo, D., & Cai, Z. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3527864 · Cited by 16
“First, according to basic differential privacy mechanism [67], we can calculate the perturbed uncorrelated representation ˆ f um = f um + Lap ( 0 , S f um /(cid:2)) by using an additional Laplace noise to satisfy (cid:2) -differential privacy, where S f um represents the global sensitivity of the…”
Differential Privacy via Distributionally Robust Optimization
Selvi, A., Liu, H., & Wiesemann, W. (2025) · Operations Research · doi:10.1287/opre.2023.0218 · Cited by 11
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.