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 901–1,000 of 1,008
Is privacy compatible with truthfulness
Xiao, D. (2011) · Cited by 11
Toward reconfigurable kernel datapaths with learned optimizations
Qiu, Y., Liu, H., Anderson, T. E., Lin, Y., & Chen, A. (2021) · Workshop on Hot Topics in Operating Systems · doi:10.1145/3458336.3465288 · Cited by 11
“For instance, if an RMT query returns some aggregate statistics, we can leverage differential privacy (DP) [18] to noise the outputs.”
BackgroundYang, Q., Zhang, Y., Dai, W., & Pan, S. J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781139061773.016 · Cited by 11
The Protection of Data Sharing for Privacy in Financial Vision
Wang, Y., & Tsai, Y. (2022) · Applied Sciences · doi:10.3390/app12157408 · Cited by 11
Bocu, R., Bocu, D., & Iavich, M. (2022) · Sensors · doi:10.3390/s23010294 · Cited by 11
“In a similar way to the referenced k-anonymity method, the differential privacy model determines several relevant metrics, which include approximate differential privacy that has weaker privacy guarantees but nevertheless ensures a greater usefulness of the de-identified data [183].”
MethodLabel Smoothing Improves Machine Unlearning
Di, Z. (2026) · Synthesis lectures on computer vision · doi:10.1007/978-3-032-17282-2_8 · Cited by 13
Differentially private GANs for generating synthetic indoor location data
Moghtadaiee, V., Alishahi, M., & Rabiei, M. (2025) · International Journal of Information Security · doi:10.1007/s10207-025-01020-4 · Cited by 11
“…the regressor/classifier learning setting, we demand that a regressor/classifier training algorithm satisfies ε -DP. ( ε, δ ) -differential privacy [34] A randomized mechanism M is ( ε, δ )-differential private if for any set S and any two neighbor databases D and The Gaussian mechanism has been…”
Using Convex Relaxations for Efficiently and Privately Releasing Marginals
Dwork, C., Nikolov, A., & Talwar, K. (2014) · Annual Symposium on Computational Geometry (SoCG) · doi:10.1145/2582112.2582123 · Cited by 11
“Definition 2.1 ([12,13]).”
InfluentialSelf-citationAnonML: Locally Private Machine Learning over a Network of Peers
Cyphers, B., & Veeramachaneni, K. K. (2017) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2017.80 · Cited by 11
“An early proposed system by Dwork [13] uses MPC and distributed Laplacian noise generation to allow a group of users to answer counting problems about their personal data with differential privacy.”
MethodChen, Y., Sheffet, O., & Vadhan, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13129-0_30 · Cited by 11
Towards Distributed Privacy-Preserving Prediction
Lyu, L., Law, Y. W., Ng, K. S., Xue, S., Zhao, J., Yang, M., & Liu, L. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283102 · Cited by 13
“More recently, Agarwal et al. [10] recalled the Binomial Mechanism [11] and provided a similar bound as ours in Theorem 1.”
BackgroundResultInfluentialDifferentially private binary- and matrix-valued data query: an XOR mechanism
Ji, T., Li, P., Yılmaz, E., Ayday, E., Ye, Y., & Sun, J. (2021) · Proceedings of the VLDB Endowment · doi:10.14778/3446095.3446106 · Cited by 11
“To handle this problem, differential privacy [13, 15] has been employed as a de facto standard for releasing privacy-preserving statistical information queries of databases.”
BackgroundMethodInfluentialOptimizing fitness-for-use of differentially private linear queries
Xiao, Y., Ding, Z., Wang, Y., Zhang, D., & Kifer, D. (2021) · Proceedings of the VLDB Endowment · doi:10.14778/3467861.3467864 · Cited by 11
“As these are complex definitions, for simplicity we focus on approximate differential privacy [16, 17], defined as follows.”
BackgroundInfluentialOn the complexity of two-party differential privacy
Haitner, I., Mazor, N., Silbak, J., & Tsfadia, E. (2022) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/3519935.3519982 · Cited by 11
Quantifying identifiability to choose and audit ϵ in differentially private deep learning
Bernau, D., Eibl, G., Grassal, P. W., Keller, H., & Kerschbaum, F. (2021) · Proceedings of the VLDB Endowment · doi:10.14778/3484224.3484231 · Cited by 16
Private Incremental Regression
Kasiviswanathan, S. P., Kobbi Nissim, B., & Jin, H. (2017) · ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS) · doi:10.1145/3034786.3034795 · Cited by 11
Yan, Y., Pei, Q., & Li, H. (2019) · IEEE Access · doi:10.1109/access.2019.2927163 · Cited by 11
“[43] propose the original ε-differential privacy.”
The More, the Better: A Study on Collaborative Machine Learning for DGA Detection
Drichel, A., Holmes, B., von Brandt, J., & Meyer, U. (2021) · CYSARM@CCS · doi:10.1145/3474374.3486915 · Cited by 13
“An extension of DP, commonly used in privacy-preserving learning, bounds the attacker’s capability of distinguishability by ε with a relaxation that exceptions to the rule may occur with a likelihood of δ [13].”
BackgroundPrivacy-Preserving Data Analytics
Quoc, D. L., Beck, M., Bhatotia, P., Chen, R., Fetzer, C. W., & Strufe, T. (2018) · Springer eBooks · doi:10.1007/978-3-319-63962-8_152-1 · Cited by 11
“of systems have been proposed with a focus on preserving user privacy (mostly, differential privacy) in a distributed setting where the private data is kept locally [37, 22, 49, 21, 45, 61, 38, 60, 28, 41, 5].”
BackgroundPractical and Bilateral Privacy-preserving Federated LearningPreprint
Feng, Y., Yang, X., Fang, W., Xia, S., & Tang, X. (2020) · arXiv (Cornell University) · Cited by 16
Benchmarking Differentially Private Residual Networks for Medical ImageryPreprint
Singh, S., Sikka, H., Kotti, S., & Trask, A. (2020) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/v2ms6 · Cited by 12
Oracle Efficient Private Non-Convex OptimizationPreprint
Neel, S., Roth, A., Vietri, G., & Wu, S. Y.-P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.01783 · Cited by 16
A bounded-noise mechanism for differential privacyPreprint
Dagan, Y., & Kur, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.03817 · Cited by 11
“What is the minimal noise-level α, such that there is an ( , δ) differentially private algorithm that answers k ∆-sensitive queries with error at most α? (namely, ∀i = 1 · · · k, |ai − qi(x)| ≤ α) One of the earliest algorithms, the Gaussian mechanism Dwork et al. (2006a), consists of adding independent Gaussian noise…”
BackgroundMethodInfluentialDecentralized Graph Neural Network for Privacy-Preserving Recommendation
Zheng, X., Wang, Z., Chen, C., Qian, J., & Yang, Y. (2023) · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management · doi:10.1145/3583780.3614834 · Cited by 10
On the local convergence of GANs with differential Privacy: Gradient clipping and noise perturbation
Azadmanesh, M., Ghahfarokhi, B. S., Talouki, M. A., & Eliasi, H. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120006 · Cited by 10
Full Differential Privacy Preserving for Switched LPV Systems
Qi, Y., Tang, Y., & Kawano, Y. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3355409 · Cited by 10
“Its definition was first proposed by Dwork et al. [5], [6].”
BackgroundELSEIR: A Privacy-Preserving Large-Scale Image Retrieval Framework for Outsourced Data Sharing
Tang, Z., Fan, H., Gu, X., Li, Y., Li, B., & Wang, X. (2024) · International Conference on Multimedia Retrieval · doi:10.1145/3652583.3658099 · Cited by 12
“While ( 𝜖,𝛿 ) -DP with 𝛿 > 0 is referred to as approximation differential privacy [2], 𝜖 -DP is typically considered pure differential privacy.”
BackgroundSu, W. (2024) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-112723-034158 · Cited by 10
Federated learning: A new frontier in the exploration of multi-institutional medical imaging data
Ciupek, D., Malawski, M., & Pieciak, T. (2026) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2026.109454 · Cited by 15
“DP adds random noise to sensitive personal characteristics, introducing some level of uncertainty in revealing individual data (Dwork et al., 2006).”
Fully Dynamic Algorithms for Graph Databases with Edge Differential Privacy
Raskhodnikova, S., & Steiner, T. A. (2025) · Proceedings of the ACM on Management of Data · doi:10.1145/3725236 · Cited by 10
The 2020 US Decennial Census is more private than you (might) think
Su, B., Su, W., & Wang, C. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2500337122 · Cited by 10
Differential Privacy and Noisy Confidentiality Concepts for European Population Statistics
Bach, F. (2021) · Journal of Survey Statistics and Methodology · doi:10.1093/jssam/smab044 · Cited by 10
Healthcare Cramér Generative Adversarial Network (HCGAN)
Indhumathi, R., & Devi, S. S. (2021) · Distributed and Parallel Databases · doi:10.1007/s10619-021-07346-x · Cited by 12
“The mechanisms used to achieve differential privacy are the Laplace mechanism [31] and the Gaussian noise mechanism [32].”
MethodSaeidian, S., Cervia, G., Oechtering, T. J., & Skoglund, M. (2022) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit50566.2022.9834814 · Cited by 10
Cooperative Differentially Private LQG Control With Measurement Aggregation
Degue, K. H., & Ny, J. L. (2022) · IEEE Control Systems Letters · doi:10.1109/lcsys.2022.3232304 · Cited by 10
“The (cid:4) 2 -sensitivity of a mapping G : Y → R is defined as The Gaussian mechanism [17] enforces ((cid:6), δ) -differential privacy by adding Gaussian noise proportional to the 2 -sensitivity of a desired mapping.”
BackgroundNode-Differentially Private Estimation of the Number of Connected Components
Kalemaj, I., Raskhodnikova, S., Smith, A., & Tsourakakis, C. E. (2023) · ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS) · doi:10.1145/3584372.3588671 · Cited by 15
“Lemma 2.4 (Composition and post-processing [21, 22]).”
InfluentialChen, H., Pang, J., Zhao, Y., Giddens, S., Ficek, J., Valente, M. J., Cao, B., & Daley, E. M. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae038 · Cited by 10
A Clinician's Guide to Sharing Data for AI in Ophthalmology
Gim, N., Wu, Y., Blazes, M. S., Lee, C. S., Wang, R. K., & Lee, A. (2024) · Investigative Ophthalmology & Visual Science · doi:10.1167/iovs.65.6.21 · Cited by 10
“19 These methods can effectively preserve the overall integrity and global information of the dataset, while substantially minimizing the risk of disclosing details about individual data points.”
MethodMean Estimation Under Heterogeneous Privacy Demands
Chaudhuri, S., Miagkov, K., & Courtade, T. A. (2024) · IEEE Transactions on Information Theory · doi:10.1109/tit.2024.3511498 · Cited by 11
“…notions of privacy have been proposed, such as K -Anonymization [9], L-diversity [10], information-theoretic notions (for example, see Asoodeh et al. [11]), and randomization techniques, the current de-facto standard for privacy – Differential Privacy (DP) – was proposed by Dwork et al. [12], [13].”
Privacy-Preserving Data Fusion
Tian, L., Turjeman, D., & Levy, S. (2026) · Marketing Science · doi:10.1287/mksc.2023.0068 · Cited by 11
Differentially private MIMO filtering for event streams and spatio-temporal monitoring
Ny, J. L., & Mohammady, M. (2014) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2014.7039716 · Cited by 10
“The privacy constraint is explained and quantified in the next subsection.”
PrivacyCanary: Privacy-Aware Recommenders with Adaptive Input Obfuscation
Kandappu, T., Friedman, A., Boreli, R., & Sivaraman, V. (2014) · Proceedings - International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems · doi:10.1109/mascots.2014.62 · Cited by 11
“Similarly, ( ,δ)-differential privacy can be obtained by perturbing the inputs with Gaussian noise N (0, σ(2)) [18], calibrated through the relation:”
BackgroundDifferentially private multi-party computation
Kairouz, P., Oh, S., & Viswanath, P. (2016) · Conference on Information Sciences and Systems · doi:10.1109/ciss.2016.7460489 · Cited by 10
“The study of accuracy-privacy tradeoffs in the MPC context was first initiated by [1] (addressed in a more general context earlier in [16]) which studied a specific paradigm where differential privacy and SFE co-exist: the function to compute is decided from differentially private analyses and the method to compute it…”
MethodDifferentially private density estimation via Gaussian mixtures model
Wu, Y., Wu, Y., Peng, H., Zeng, J., Chen, H., & Li, C. (2016) · International Workshop on Quality of Service · doi:10.1109/iwqos.2016.7590445 · Cited by 10
“A popular paradigm for providing privacy with strong theoretical guarantees is differential privacy [3], [4], which has recently gained significant attention in the data analysis communities for its robustness to known attacks, such as those involving side information [5].”
BackgroundDo Distributed Differentially-Private Protocols Require Oblivious Transfer?
Goyal, V., Khurana, D., Mironov, I., Pandey, O., & Sahai, A. (2016) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.icalp.2016.29 · Cited by 10
Self-citationPrivacy-Preserving Publication of Deep Neural Networks
Sei, Y., Okumura, H., & Ohsuga, A. (2016) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-smartcity-dss.2016.0202 · Cited by 11
“Moreover, they use ( , δ)-differential privacy [22], which relaxes the -differential privacy as their privacy metric.”
BackgroundKenthapadi, K., Chudhary, A., & Ambler, S. (2017) · IEEE Symposium on Privacy-Aware Computing (PAC) · doi:10.1109/pac.2017.9 · Cited by 12
Self-citationThe Philosophy of Differential Privacy
Bowen, C. M., & Garfinkel, S. (2021) · Notices of the American Mathematical Society · doi:10.1090/noti2363 · Cited by 10
Multiparty Reach and Frequency Histogram: Private, Secure, and Practical
Ghazi, B., Kreuter, B., Kumar, R., Manurangsi, P., Peng, J., Skvortsov, E., Wang, Y., & Wright, C. (2021) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2022-0019 · Cited by 15
“Definition 1 (Differential Privacy (DP) [28, 29]) .”
MethodPrivacy-Preserving Vertical Federated Logistic Regression without Trusted Third-Party Coordinator
Sun, H., Wang, Z., Huang, Y., & Ye, J. (2022) · International Conference on Machine Learning and Soft Computing (ICMLSC) · doi:10.1145/3523150.3523171 · Cited by 10
“Thus, each party needs to use privacy protection technologies like homomorphic encryption (HE) [2, 20], secure multi-party computing [9], and differential privacy (DP) [4, 5] to protect its data privacy.”
BackgroundPrivateMail: Supervised Manifold Learning of Deep Features with Privacy for Image Retrieval
Vepakomma, P., Balla, J., & Raskar, R. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20827 · Cited by 10
“One popular private mechanism is the Gaussian mechanism (Dwork et al. 2006), which adds Gaussian noise depending on the query’s sensitivity.”
BackgroundWhen Differential Privacy Implies Syntactic Privacy
Ekenstedt, E., Ong, L., Liu, Y., Johnson, S. J., Yeoh, P. L., & Kliewer, J. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3177953 · Cited by 10
Zhang, Y., Qu, Y., Gao, L., Luan, T. H., Jolfaei, A., & Zheng, X. (2023) · Sustainable Energy Technologies and Assessments · doi:10.1016/j.seta.2023.103144 · Cited by 16
One Step to Efficient Synthetic Data
Awan, J., & Cai, Z. (2023) · Statistica Sinica · doi:10.5705/ss.202022.0274 · Cited by 12
“The concept of differential privacy (DP) was proposed in Dwork et al. [2006b] as a framework to develop methods of preserving privacy, with mathematical guarantees.”
BackgroundMethodInfluentialICL: An Incentivized Collaborative Learning Framework
Wang, X., Le, Q., Khan, A., Ding, J., & Anwar, A. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825643 · Cited by 10
“For instance, future studies could examine the functional forms of pricing plans, use cases to promote model security [46, 47] and privacy [48], and trade-offs between collaboration and competition.”
Privacy-Preserving Stream Aggregation with Fault Tolerance.
Chan, T.-H. H., Shi, E., & Song, D. X. (2011) · Cited by 10
Network Coding for Federated Learning Systems
Kong, L., Tao, H., Wang, J., Huang, Z., & Xiao, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63833-7_46 · Cited by 10
An Investigation towards Differentially Private Sequence Tagging in a Federated Framework
Jana, A., & Biemann, C. (2021) · Workshop on Privacy in Natural Language Processing (PrivateNLP) · doi:10.18653/v1/2021.privatenlp-1.4 · Cited by 16
“To mitigate such inference attacks, differential privacy (Dwork et al., 2006) was developed, which comes with a theoretically guaranteed measurement of privacy.”
BackgroundLearning Model-Based Privacy Protection under Budget Constraints
Hong, J., Wang, H., Wang, Z., & Zhou, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i9.16941 · Cited by 10
“Both mechanisms rely on querying the model outputs for several times via an exponential noise mechanism (Dwork 2006) which degrades the effectiveness.”
BackgroundEnabling accurate analysis of private network data
Miklau, G., Jensen, D. D., & Hay, M. (2010) · Cited by 10
Practical Distributed Privacy-Preserving Data Analysis at Large Scale
Duan, Y., & Canny, J. (2013) · Springer eBooks · doi:10.1007/978-1-4614-9242-9_8 · Cited by 11
“, [1, 9, 10, 35, 57, 60–62, 64]).”
BackgroundRoot ORAM: A Tunable Differentially Private Oblivious RAMPreprint
Wagh, S., Cuff, P., & Mittal, P. (2016) · arXiv (Cornell University) · Cited by 10
Formal Privacy for Functional Data with Gaussian PerturbationsPreprint
Mirshani, A., Reimherr, M. L., & Slavković, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.06660 · Cited by 10
“Using classic results from univariate DP (e.g. Dwork et al., 2006a), a private version would be where Here ∆ j denotes the scalar global sensitivity of (cid:104) X, v j (cid:105) with respect to (cid:104) Z , v j (cid:105) .”
BackgroundMethodThe power of the hybrid model for mean estimation
Avent, B., Dubey, Y., & Korolova, A. (2020) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2020-0062 · Cited by 9
A Privacy-Preserving Querying Mechanism with High Utility for Electric Vehicles
Atmaca, U. I., Biswas, S., Maple, C., & Palamidessi, C. (2024) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2024.3360302 · Cited by 9
“Definition 3.1 (Differential privacy [13], [14]): For a certain query, a randomizing mechanism R provides (cid:2) -DP if, for all neighbouring 1 datasets, D and D (cid:2) , and all S ⊆ Range( R ), we have A major drawback of the central model is that it is vulnerable to security breaches because the…”
BackgroundInfluentialFlow-Based Distributionally Robust Optimization
Xu, C., Lee, J., Cheng, X., & Xie, Y. (2024) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2024.3370699 · Cited by 24
“Established by [17], [18], differential privacy (DP) offers a structured method to measure how well individual privacy is secured in a database when collective data insights are shared as answers to the query.”
BackgroundHe, C., Wang, Y., Hu, J., Luan, T. H., Bi, Y., & Su, Z. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3461855 · Cited by 9
Loki: A privacy-conscious platform for crowdsourced surveys
Kandappu, T., Sivaraman, V., Friedman, A., & Boreli, R. (2014) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets.2014.6734877 · Cited by 12
“The paper is concluded in §VII.”
Yang, J., Wu, J., & Wang, X. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2020.0078 · Cited by 9
RetractedCross-Silo Process Mining with Federated Learning
Khan, A., Ghose, A., & Dam, H. K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91431-8_38 · Cited by 9
Bartan, B., & Pilancı, M. (2023) · IEEE Transactions on Information Theory · doi:10.1109/tit.2023.3247559 · Cited by 9
“Definition 5.1 ((ε, δ)-Differential Privacy, [36], [37]): An algorithm ALG which maps (n × d)-matrices into some range R satisfies (ε, δ)-differential privacy if for all pairs of neighboring inputs A and A′ (i.e. they differ only in a single row) and all subsets S ⊂ R, it holds that P (ALG(A) ∈ S) ≤ eεP (ALG(A′) ∈ S)…”
BackgroundInfluentialConcurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters
Haney, S., Shoemate, M., Tian, G., Vadhan, S., Vyrros, A., Xu, V., & Zhang, W. (2023) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3576915.3623128 · Cited by 9
Wang, J., Chang, X., Mišić, J., Mišić, V. B., Chen, Z., & Fan, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3360007 · Cited by 11
“Now, we give the definition of DP in (2) ( Notably, if δ ∈ [0 , 1 ) satisfies δ = 0, the mechanism M is -DP, which is pure without relaxation probability [35].”
BackgroundWasserstein Differential Privacy
Yang, C., Qi, J., & Zhou, A. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i15.29565 · Cited by 15
Yang, Z., Wei, Y., Li, H., Li, Q., Jiang, L., Sun, L., Yu, X., Hu, C., & Peng, H. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679537 · Cited by 9
A Framework for Differential Privacy Against Timing Attacks
Ratliff, Z. B., & Vadhan, S. (2024) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3658644.3690206 · Cited by 9
Efficient Verifiable Differential Privacy with Input Authenticity in the Local and Shuffle Model
Bontekoe, T., Asghar, H. J., & Türkmen, F. (2025) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2025-0076 · Cited by 9
Verified indifferentiable hashing into elliptic curves
Barthe, G., Grégoire, B., Heraud, S., Olmedo, F., & Zanella-Béguelin, S. (2013) · Journal of Computer Security · doi:10.3233/jcs-130476 · Cited by 9
“1, the α -distance between μ 1 and μ 2 as This generalization allows reasoning about differential privacy [20].”
Robust Fully Distributed Minibatch Gradient Descent with Privacy Preservation
Danner, G., Berta, Á., Hegedűs, I., & Jelasity, M. (2018) · Security and Communication Networks · doi:10.1155/2018/6728020 · Cited by 13
“In our distributed setup, this noise term can be computed in a distributed and secure way [17].”
BackgroundLearning Privately with Labeled and Unlabeled Examples
Beimel, A., Kobbi Nissim, B., & Stemmer, U. (2014) · ACM-SIAM Symposium on Discrete Algorithms (SODA) · doi:10.1137/1.9781611973730.32 · Cited by 23
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
Zheng, Q., Dong, J., Long, Q., & Su, W. (2020) · PubMed · doi:10.48550/arxiv.2003.04493 · Cited by 25
A Neuron Noise-Injection Technique for Privacy Preserving Deep Neural Networks
Adesuyi, T. A., & Kim, B. M. (2020) · Open Computer Science · doi:10.1515/comp-2020-0133 · Cited by 9
“The approach uses random noise to guarantee that noticeable information does not change much even when a record is altered in the database [22, 23]. ϵ -differential privacy is currently perceived as an incontestable mechanism to guarantee privacy [24] in an advent of a malicious intruder having…”
MethodImproved Differentially Private Euclidean Distance Approximation
Stausholm, N. M. (2021) · ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS) · doi:10.1145/3452021.3458328 · Cited by 9
“Privacy follows directly from the Gaussian mechanism (see Lemma 2), as the ℓ 2 -sensitivity is at most 1 (clearly, as we perturb the input vectors).”
BackgroundInfluentialDifferentially private transferrable deep learning with membership-mappings
Kumar, M. (2022) · Advances in Computational Intelligence · doi:10.1007/s43674-022-00049-5 · Cited by 11
“Keywords Privacy · Deep learning · Fuzzy · Transfer learning”
BackgroundInfluentialRRN: A differential private approach to preserve privacy in image classification
Shen, Z., Zhong, T., Sun, H., & Qi, B. (2023) · IET Image Processing · doi:10.1049/ipr2.12784 · Cited by 9
Privacy-Preserving Federated Cross-Domain Social Recommendation
Cai, J., Liu, Y., Liu, X., Li, J., & Zhuang, H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-28996-5_11 · Cited by 10
“…, a random algorithm A satisfies ε -DP if its all outputs O ∈ Range ( A ) satisfies Traditional DP mechanisms are mostly for continuous and discrete data, such as Laplace mechanism [Dwork et al. , 2006b] for continuous data and Exponential mechanism [Mc-Sherry and Talwar, 2007] for discrete data.”
BackgroundDifferentially Private Heatmaps
Ghazi, B., He, J., Kohlhoff, K., Kumar, R., Manurangsi, P., Navalpakkam, V., & Valliappan, N. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i6.25933 · Cited by 16
Analyzing the Shuffle Model Through the Lens of Quantitative Information Flow
Jurado, M., Gonze, R. G., Alvim, M. S., & Catuscia Palamidessi, A. (2023) · IEEE Computer Security Foundations Workshop (CSFW) · doi:10.1109/csf57540.2023.00033 · Cited by 10
“Differential privacy (DP), introduced by Dwork and her colleagues [1], [2], is one of the most successful frameworks for privacy protection.”
BackgroundBlinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning
Yang, X., & Ardakanian, O. (2023) · ACM Transactions on Sensor Networks · doi:10.1145/3623397 · Cited by 14
“Differential privacy (DP) [5, 25] provides mathematically verifiable privacy guarantees by adding perturbations to the data.”
BackgroundDifferential Privacy Under Membership Inference Attacks
Ha, T., Vo, T., Dang, T. K., & Trang, N. T. H. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-8296-7_18 · Cited by 9
Shibata, H., Hanaoka, S., Nakao, T., Kikuchi, T., Nakamura, Y., Nomura, Y., Yoshikawa, T., & Abe, O. (2024) · Applied Sciences · doi:10.3390/app14083489 · Cited by 9
Sensitive Disclosures under Differential Privacy Guarantees
Han, C., & Wang, K. (2015) · IEEE International Congress on Big Data (BigData Congress) · doi:10.1109/bigdatacongress.2015.25 · Cited by 10
“To our knowledge, Corollary 1 covers all noise distributions employed by the differential privacy mechanism, including Laplace mechanism [27], Gaussian mechanism [30], and Matrix mechanism [55], because these distributions have a zero mean and a fixed variance.”
On differentially private filtering for event streams
Ny, J. L. (2013) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2013.6760417 · Cited by 9
Engineering Methods for Differentially Private Histograms: Efficiency Beyond Utility
Kellaris, G., Papadopoulos, S., & Dimitris Papadias, C. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2827378 · Cited by 9
On the Tradeoff Between Data-Privacy and Utility for Data Publishing
Liao, W., He, J., Zhu, S., Chen, C., & Guan, X. (2018) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/padsw.2018.8644952 · Cited by 9
“al [25] investigate the optimal noise under differential privacy and conclude the optimal noise to be Laplace noise.”
BackgroundEnhance PATE on Complex Tasks With Knowledge Transferred From Non-Private Data
Wang, L., Zheng, J., Cao, Y., & Wang, H. (2019) · IEEE Access · doi:10.1109/access.2019.2910885 · Cited by 10
“To formalize this intuition, one of the definitions was given by [33], Definition 1: A randomizedmechanismMwith domainD and rangeR satisfies ( , δ)-differential privacy if for any two adjacent datasets (differing at most one record) d , d ′ ∈ D and for any subset of outputs S ⊆ R, it holds that”
MethodPrivacy-Preserving Distributed Projection LMS for Linear Multitask Networks
Wang, C., Tay, W. P., Wei, Y., & Wang, Y. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3126929 · Cited by 10
Privacy Risks in Vehicle Grids and Autonomous Cars
Joy, J., & Gerla, M. (2017) · ACM International Workshop on Smart, Autonomous, and Connected Vehicular Systems and Services (CarSys) · doi:10.1145/3131944.3133938 · Cited by 9
The Trade-Off Between Privacy and Fidelity via Ehrhart Theory
Padakandla, A., Kumar, P. R., & Szpankowski, W. (2019) · IEEE Transactions on Information Theory · doi:10.1109/tit.2019.2959976 · Cited by 9
“In fact, the notion of approximate DP [23] was motivated by this observation.”
BackgroundPrivacy-Preserving Pedestrian Detection for Smart City with Edge Computing
Yuan, D., Zhu, X., Mao, Y., Zheng, B., & Wu, T. (2019) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2019.8927923 · Cited by 10
“[11] and the exponential Mechanism [12].”
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.