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 201–300 of 1,008
Differentially Private Naive Bayes Classification
Vaidya, J. S., Shafiq, B., Basu, A., & Hong, Y. (2013) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2013.80 · Cited by 131
“Indeed, the recent differentially private algorithms follow the same line of research to build queries or data analysis application by adding noise [7] or running particular randomization mechanism [13], [17] to achieve quantifiable notion of privacy.”
BackgroundNear-optimal Differentially Private Principal Components
Chaudhuri, K., Sarwate, A. D., & Sinha, K. P. (2012) · Cited by 104
Lightweight Techniques for Private Heavy Hitters
Boneh, D., Boyle, E., Corrigan-Gibbs, H., Gilboa, N., & Ishai, Y. (2021) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp40001.2021.00048 · Cited by 142
Feldman, D., Fiat, A., Kaplan, H. Y., & Kobbi Nissim, B. (2009) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/1536414.1536465 · Cited by 104
“INTRODUCTION The notion of Differential privacy [18] has emerged in a recent line of work on private data analysis that seeks a rigorous treatment of privacy and its consequences (see [15, 22, 20, 7, 18, 17, 16, 40, 19, 37, 5, 41, 8, 6, 21, 35]).”
BackgroundThe Geometry of Differential Privacy: the Sparse and Approximate Cases
Nikolov, A., Talwar, K., & Zhang, L. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1212.0297 · Cited by 94
An adaptive mechanism for accurate query answering under differential privacy
Li, C., & Miklau, G. (2012) · Proceedings of the VLDB Endowment · doi:10.14778/2168651.2168653 · Cited by 105
“Approximate differential privacy can be achieved by adding Gaussian noise calibrated to the L2 sensitivity of the queries [9, 17].”
BackgroundTowards formalizing the GDPR’s notion of singling out
Cohen, A., & Kobbi Nissim, B. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1914598117 · Cited by 103
“Definition 6.1 [ Differential Privacy (10, 19)] A randomized mechanism M : X n → T is ( ε , δ ) -differentially private if for all x , x (cid:48) ∈ X n , x ∼ x (cid:48) and for all events S ⊆ T , where the probability is taken over the randomness of the mechanism M .”
InfluentialEfficient Deep Learning on Multi-Source Private Data
Hynes, N., Cheng, R., & Song, D. X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.06689 · Cited by 73
“Formally, for all datasets D i , D j ∈ D D i , D j which differ in a single entry, if [10].”
BackgroundProbabilistic relational reasoning for differential privacy
Barthe, G., Köpf, B., Olmedo, F., & Zanella-Béguelin, S. (2012) · ACM SIGPLAN Notices · doi:10.1145/2103621.2103670 · Cited by 102
Data Anonymization for Pervasive Health Care: Systematic Literature Mapping Study
Zuo, Z., Watson, M., Budgen, D., Hall, R., Kennelly, C., & Moubayed, N. A. (2021) · JMIR Medical Informatics · doi:10.2196/29871 · Cited by 122
Talwar, K. (2022) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.48550/arxiv.2202.10618 · Cited by 102
“This approach goes back to the early days of differential privacy [16], and has been heavily investigated [11, 8].”
Differentially Private Fine-tuning of Language Models
Yu, D., Naik, S., Backurs, A., Gopi, S., Inan, H. A., Kamath, G., Kulkarni, J., Lee, Y. T., Manoel, A., Wutschitz, L., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.06500 · Cited by 101
Probabilistic Relational Reasoning for Differential Privacy
Barthe, G., Köpf, B., Olmedo, F., & Zanella-Béguelin, S. (2013) · ACM Transactions on Programming Languages and Systems · doi:10.1145/2492061 · Cited by 101
Privacy and Statistical Risk: Formalisms and Minimax BoundsPreprint
Barber, R. F., & Duchi, J. C. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.4451 · Cited by 101
New Efficient Attacks on Statistical Disclosure Control Mechanisms
Dwork, C., & Yekhanin, S. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85174-5_26 · Cited by 100
“Provably secure mechanisms are now available [3, 9, 16, 18] for many standard data-mining tasks such as singular value decomposition, k-means clustering, principal component analysis, the perceptron algorithm, and contingency table release, several tasks in learning theory [4, 9, 20], and distributed implementations o…”
BackgroundSelf-citationTalwar, K. (2022) · Leibniz international proceedings in informatics · doi:10.4230/lipics.forc.2022.7 · Cited by 104
Practical differential privacy via grouping and smoothing
Kellaris, G., & Papadopoulos, S. (2013) · Proceedings of the VLDB Endowment · doi:10.14778/2535573.2488337 · Cited by 100
“Variations of ǫ-differential privacy There exist two relaxations of ǫ-differential privacy; (ǫ, δ)-probabilistic differential privacy [13] and (ǫ, δ)-indistinguishability [5, 16].”
BackgroundRemember What You Want to Forget: Algorithms for Machine Unlearning
Sekhari, A., Acharya, J., Kamath, G., & Suresh, A. T. (2021) · arXiv · doi:10.48550/arxiv.2103.03279 · Cited by 99
“…requirement is rather strong: Ginart et al. (2019) proposed a relaxed notion of deletion, in which the model must only be close to the alternative, where closeness is defined in a way reminiscent of differential privacy (Dwork et al., 2006b,a) (our variant of this notion is described in Definition 2).”
BackgroundOptimal Noise Adding Mechanisms for Approximate Differential Privacy
Geng, Q., & Viswanath, P. (2016) · IEEE Transactions on Information Theory · doi:10.1109/tit.2015.2504972 · Cited by 91
Private Stochastic Convex Optimization with Optimal Rates
Bassily, R., Feldman, V., Talwar, K., & Thakurta, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.09970 · Cited by 75
“Differential privacy [DMNS06, DKM + 06]: A randomized algorithm A is ( (cid:15), δ ) -differentially private if, for any pair of datasets S and S (cid:48) differ in exactly one data point, and for all events O in the output range of A , we have where the probability is taken over the random coins…”
BackgroundInternet of Vehicles and Autonomous Connected Car - Privacy and Security Issues
Joy, J., & Gerla, M. (2017) · 2017 26th International Conference on Computer Communication and Networks (ICCCN) · doi:10.1109/icccn.2017.8038391 · Cited by 90
“Differential privacy [3], [4], [5], [6] has been proposed as a mechanism to privately share data such that anything that can be learned if a particular data owner is included in the database”
BackgroundConsensus-Based Data-Privacy Preserving Data Aggregation
He, J., Cai, L., Cheng, P., Pan, J., & Shi, L. (2019) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2019.2910171 · Cited by 100
Grataloup, A., Jonas, S., & Meyer, A. (2024) · Energy and AI · doi:10.1016/j.egyai.2024.100375 · Cited by 116
“Differential privacy [54] provides a security guarantee enabling calculating operations over a dataset while restricting the information that can be retrieved about a specific dataset sample.”
Private stochastic convex optimization: optimal rates in linear time
Feldman, V., Koren, T., & Talwar, K. (2020) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/3357713.3384335 · Cited by 222
Shredder: Learning Noise Distributions to Protect Inference Privacy
Mireshghallah, F., Taram, M., Ramrakhyani, P., Jalali, A., Tullsen, D. M., & Esmaeilzadeh, H. (2020) · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · doi:10.1145/3373376.3378522 · Cited by 133
“The idea of noise injection for privacy goes back at least to the very first differential privacy papers [23, 59] where they randomize the result of a query to a database by adding noise drawn from a Laplace distribution.”
BackgroundTransfer Learning in Natural Language Processing
Yang, Q., Zhang, Y., Dai, W., & Pan, S. J. (2020) · Cambridge University Press eBooks · doi:10.1017/9781139061773.020 · Cited by 95
Practical Data Synthesis for Large Samples
RAAB, G. M., Nowok, B., & Dibben, C. J. L. (2018) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.v7i3.407 · Cited by 94
“An extension to this method, -δ-differential privacy Dwork et al. (2006); Dwork and Smith (2011), which allows a mechanism (e.g. a synthesis) to satisfy -differential privacy with probability 1− δ, has been used to generate the syn- thetic data that sit behind the U.S. Bureau of the Census’s…”
MethodThe Complexity of Computing the Optimal Composition of Differential Privacy
Murtagh, J., & Vadhan, S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-662-49096-9_7 · Cited by 75
Distributed Key Generation for Encrypted Deduplication: Achieving the Strongest Privacy
Duan, Y. (2014) · doi:10.1145/2664168.2664169 · Cited by 93
“This situation bears an interesting parallel to the challenge in statistical database privacy, which studies the problem of releasing statistical patterns of the data while preserving the privacy of each individual record [20, 26, 15, 35, 34, 46].”
BackgroundCombining Differential Privacy and Secure Multiparty Computation
Pettai, M., & Laud, P. (2015) · Annual Computer Security Applications Conference · doi:10.1145/2818000.2818027 · Cited by 94
“Differentially private data aggregation has received a lot of interest [13, 1, 19], but typically without employing SMC.”
Putting Statistical Disclosure Control into Practice: The ARX Data Anonymization Tool
Praßer, F., & Kohlmayer, F. (2015) · Springer eBooks · doi:10.1007/978-3-319-23633-9_6 · Cited by 93
InstaHide: Instance-hiding Schemes for Private Distributed LearningPreprint
Huang, Y., Song, Z., Li, K., & Arora, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.02772 · Cited by 111
“On top of that, it is possible to add noise to gradients in accordance with Differential Privacy (DP) (Dwork et al., 2006; Dwork & Roth, 2014), though careful calculations are needed to compute the amount of noise to be added (Abadi et al.”
BackgroundLinkedIn's Audience Engagements API: A Privacy Preserving Data Analytics System at Scale
Rogers, R., Subramaniam, S., Peng, S. X., Durfee, D., Lee, S., Kancha, S. K., Sahay, S., & Ahammad, P. (2021) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.782 · Cited by 92
Understanding Tor Usage with Privacy-Preserving Measurement
Mani, A., Wilson-Brown, T., Jansen, R., Johnson, A., & Sherr, M. (2018) · ACM Internet Measurement Conference (IMC) · doi:10.1145/3278532.3278549 · Cited by 111
“More formally, a ( δ, (cid:15) )- differentially private mechanism [20] is an algorithm M such that for all adjacent databases D 1 and D 2 and all S ⊆ Range( ), where δ and (cid:15) are parameters that can be used to trade off between privacy and accuracy.”
BackgroundInference using noisy degrees: Differentially private $\beta$-model and synthetic graphs
Karwa, V., & Slavković, A. (2015) · The Annals of Statistics · doi:10.1214/15-aos1358 · Cited by 91
“Lemma 1 (Post-processing, [2, 11]) .”
Differential privacy in deep learning: A literature survey
Pan, K., Ong, Y.-S., Gong, M., Li, H., Qin, A. K., & Gao, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127663 · Cited by 113
Private Analysis of Graph Structure
Karwa, V., Raskhodnikova, S., Smith, A., & Yaroslavtsev, G. (2014) · ACM Transactions on Database Systems · doi:10.1145/2611523 · Cited by 111
“4The algorithms of Gehrke et al. [2011] satisfy a stronger notion, namely zero-knowledge privacy, but assume a known (small) upper bound on the degree of all vertices.”
BackgroundMethodInfluentialBatool, H., Anjum, A., Khan, A., Izzo, S., Mazzocca, C., & Jeon, G. (2024) · Information Sciences · doi:10.1016/j.ins.2023.119717 · Cited by 89
Privacy-aware personalization for mobile advertising
Hardt, M., & Nath, S. (2012) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/2382196.2382266 · Cited by 88
“One might use a distributed privacy-preserving aggregation protocol [1, 12, 37, 40] to compute such statistics.”
BackgroundMethodInfluentialEncode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation
Erlingsson, Ú., Feldman, V., Mironov, I., Raghunathan, A., Song, S., Talwar, K., & Thakurta, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.03618 · Cited by 33
“The most common definition of this metric is based on the worst-case replacement of any dataset record: [25]) .”
BackgroundSelf-citationSun, C., van Soest, J., & Dumontier, M. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104404 · Cited by 97
Towards robustness in query auditing
Nabar, S. U., Marthi, B., Kenthapadi, K., Mishra, N., & Motwani, R. (2006) · doi:10.5555/1182635.1164142 · Cited by 86
Self-citationDifferentially Private Data Generative ModelsPreprint
Chen, Q., Xiang, C., Xue, M., Li, B., Borisov, N., Kaarfar, D., & Zhu, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.02274 · Cited by 100
“A common approach to achieving differential privacy is to add noise from Laplacian [20] or Gaussian distribution [21] whose variance is determined by the privacy budget.”
BackgroundPrivacy-Preserving Collaborative Deep Learning with Application to Human Activity Recognition
Lyu, L., He, X., Law, Y. W., & Palaniswami, M. (2017) · Proceedings of the 2017 ACM on Conference on Information and Knowledge Management · doi:10.1145/3132847.3132990 · Cited by 81
“’s scheme [11] requires participants to communicate with each other (in addition to the cloud service), and use verifiable secret sharing to generate shares of random noise, imposing computational and communication costs on the order of 2t , where t is the estimated maximum number of dishonest participants.”
BackgroundGarrido, G. M., Sedlmeir, J., Uludağ, Ö., Alaoui, I. S., Luckow, A., & Matthes, F. (2022) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2022.103465 · Cited by 97
Optimal Lower Bound for Differentially Private Multi-party Aggregation
Chan, T.-H. H., Shi, E., & Song, D. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33090-2_25 · Cited by 82
Is privacy compatible with truthfulness?
Xiao, D. (2013) · Conference on Innovations in Theoretical Computer Science · doi:10.1145/2422436.2422448 · Cited by 82
Differentially Private Smart Metering with Battery Recharging
Michael Backes, A., & Meiser, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-642-54568-9_13 · Cited by 82
“Prior work on differential privacy in smart metering or on the smart use of batteries to achieve privacy guarantees comprises [3, 4, 10, 12, 17, 20, 25, 27, 28].”
BackgroundPrivacy Amplification by Iteration
Feldman, V., Mironov, I., Talwar, K., & Thakurta, A. (2018) · 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS) · doi:10.1109/focs.2018.00056 · Cited by 80
“In the “Our data, ourselves” model proposed by [9], each user’s device holds their data, and there is no central trusted party.”
BackgroundSelf-citationA Survey of Privacy Vulnerabilities of Mobile Device Sensors
Delgado-Santos, P., Stragapede, G., Tolosana, R., Guest, R., Deravi, F., & Vera-Rodríguez, R. (2022) · ACM Computing Surveys · doi:10.1145/3510579 · Cited by 93
“has less strict privacy guarantees but is able to retain a higher utility [53].”
BackgroundAnonymizing Data for Privacy-Preserving Federated LearningPreprint
Choudhury, O., Gkoulalas-Divanis, A., Salonidis, T., Sylla, I., Park, Y., Hsu, G., & Das, A. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09096 · Cited by 102
“A majority of recent work have adopted -differential privacy (DP) [14] for protecting FL models against such attacks.”
BackgroundEfficient, Differentially Private Point EstimatorsPreprint
Smith, A. (2008) · arXiv (Cornell University) · doi:10.48550/arxiv.0809.4794 · Cited by 86
“A recent line of work [11, 20, 18, 4, 16, 15, 12, 29, 17, 27, 3, 30, 5, 19, 25, 24], called private data analysis , seeks to place data privacy on more firm theoretical foundations and has been successful at formulating a strong, yet attainable privacy definition.”
BackgroundWang, Y.-X., Lei, J., & Fienberg, S. E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.06309 · Cited by 74
“Definition 27 (Dwork et al., 2006a).”
BackgroundMethodAn efficient data aggregation scheme with local differential privacy in smart grid
Gai, N., Xue, K., Zhu, B., Yang, J., Liu, J., & He, D. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2022.01.004 · Cited by 78
Near) Dimension Independent Risk Bounds for Differentially Private Learning
Jain, P., & Thakurta, A. (2014) · Cited by 78
Hyperparameter Tuning with Renyi Differential PrivacyPreprint
Papernot, N., & Steinke, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03620 · Cited by 112
“The definition of pure DP was introduced by Dwork et al. (2006b) and approximate DP was introduced by Dwork et al. (2006a).”
BackgroundInfluentialSurvey: Leakage and Privacy at Inference Time
Jegorova, M., Kaul, C., Mayor, C., O'Neil, A. Q., Weir, A., Murray-Smith, R., & Tsaftaris, S. A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3229593 · Cited by 77
“For instance, ð ; dÞ-differential privacy, [154], guarantees that with probability of at most ð1 dÞ the privacy loss does not exceed .”
BackgroundDJoin: differentially private join queries over distributed databases
Narayan, A., & Haeberlen, A. (2012) · Operating Systems Design and Implementation · doi:10.5555/2387880.2387895 · Cited by 119
Reasoning About Generalization via Conditional Mutual InformationPreprint
Steinke, T., & Zakynthinou, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.09122 · Cited by 191
“Any one of the following conditions imply that CMID (A) ≤ εn for any distribution D. (i) A is √ 2ε-differentially private (Dwork et al., 2006).”
BackgroundDiverse Grouping-Based Aggregation Protocol With Error Detection for Smart Grid Communications
Shi, Z., Sun, R., Lu, R., Chen, L., Chen, J., & Shen, X. (2015) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2015.2443011 · Cited by 76
“As a result, the proposed DG-APED achieves the confidentiality, i.e., the information is secure against the external attacker’s eavesdropping attack on data aggregation communications.”
BackgroundProtecting Location Privacy for Task Allocation in Ad Hoc Mobile Cloud Computing
Gong, Y., Zhang, C., Fang, Y. M., & Sun, J. (2015) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2015.2490021 · Cited by 76
“The privacy guarantee provided in our framework is -differential privacy [19], [20].”
BackgroundNumerical Composition of Differential Privacy
Gopi, S., Lee, Y. T., & Wutschitz, L. (2024) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.870 · Cited by 79
Privacy-utility tradeoff under statistical uncertainty
Makhdoumi, A., & Fawaz, N. (2013) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2013.6736724 · Cited by 91
Discrete Gaussian for Differential Privacy
Canonne, C. L., Kamath, G., & Steinke, T. (2022) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.784 · Cited by 85
“Differential Privacy [DMNS06, DKM + 06] provides a rigorous standard for ensuring that the output of an algorithm does not leak the private details of individuals contained in its input.”
BackgroundEnabling Verifiable Privacy-Preserving Multi-Type Data Aggregation in Smart Grids
Zhang, X., Huang, C., Zhang, Y., & Cao, S. (2021) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3124546 · Cited by 74
“Some researches use noise to preserve privacy of users’ data, namely differential privacy [56].”
BackgroundOn differentially private low rank approximation
Kapralov, M., & Talwar, K. (2013) · doi:10.5555/2627817.2627918 · Cited by 74
Private PAC learning implies finite Littlestone dimension
Alon, N., Livni, R., Malliaris, M., & Moran, S. (2019) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/3313276.3316312 · Cited by 145
“[19, 20] If p,q are (ε,δ )-indistinguishable then for all k ∈ N, pk and qk are (kε,kδ )-indistinguishable, where pk ,qk are the k-fold products of p,q (i.”
BackgroundCoupled-Worlds Privacy: Exploiting Adversarial Uncertainty in Statistical Data Privacy
Bassily, R., Groce, A., Katz, J. I., & Smith, A. (2013) · Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2013.54 · Cited by 73
“A mechanism F satisfies ( , δ,Δ)-distributional differential privacy if there is a simulator Sim such that for all distributions D ∈ Δ on (X,Z), all i, and all (xi, z) ∈ Supp(Xi, Z): F (X) ∣∣ Xi=xi, Z=z ≈ ,δ Sim(X−i) ∣∣ Xi=xi, Z=z .”
LightDP: towards automating differential privacy proofs
Zhang, D., & Kifer, D. (2016) · ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL) · doi:10.1145/3009837.3009884 · Cited by 95
“…answer queries, and build statistical models satisfy differential privacy (Dwork et al. 2006b) — a set of restrictions on their probabilistic behavior that provably limit the ability of attackers to infer individual-level sensitive information (Dwork et al. 2006b; Kifer and Machanavajjhala 2014).”
BackgroundDistributed Privacy-Preserving Data Aggregation Against Dishonest Nodes in Network Systems
He, J., Cai, L., Cheng, P., Pan, J., & Shi, L. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2834544 · Cited by 73
“[27] designed a distributed random noise generation protocol aiming at a distributed implementation of privacy-preserving statistical databases.”
BackgroundCompressive mechanism: utilizing sparse representation in differential privacy
Li, Y. D., Zhang, Z., Winslett, M., & Yang, Y. (2011) · ACM Workshop on Privacy in the Electronic Society (WPES) · doi:10.1145/2046556.2046581 · Cited by 91
“Alternative definitions soon appeared, such as (ǫ, δ)-differential privacy [20, 40], pan-privacy [24, 23] and zero-knowledge privacy [25].”
BackgroundPrivate Learning and Sanitization: Pure vs. Approximate Differential Privacy
Beimel, A., Nissim, K., & Stemmer, U. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-40328-6_26 · Cited by 72
A Blockchain-Based Federated Learning Scheme for Data Sharing in Industrial Internet of Things
Xu, G., Zhou, Z., Dong, J., Zhang, L., & Song, X. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3298196 · Cited by 78
“DP [34] can protect data privacy while maximizing query accuracy, generally by adding randomized noise [35] to avoid attackers from accessing raw IIoT data.”
BackgroundDifferentially private distributed logistic regression using private and public data
Ji, Z., Jiang, X., Wang, S., Xiong, L., & Ohno-Machado, L. (2014) · BMC Medical Genomics · doi:10.1186/1755-8794-7-s1-s14 · Cited by 72
“Differential privacy (DP) is a privacy definition proposed by Dwork, Kenthapadi, McSherry et al [8], which states that any answer to a query based on a private data set should not be altered dramatically with the change of a single record in the data set.”
BackgroundExponential random graph estimation under differential privacy
Lu, W., & Miklau, G. (2014) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2623330.2623683 · Cited by 71
“Definition 2.1 (Differential Privacy[7]) .”
InfluentialAnoA: A Framework for Analyzing Anonymous Communication Protocols
Michael Backes, A., Kate, A., Manoharan, P., Meiser, S., & Mohammadi, E. (2013) · IEEE Computer Security Foundations Workshop (CSFW) · doi:10.1109/csf.2013.18 · Cited by 71
“t αSA for Tor to more than one challenge row, we can use the direct amplification approach also known from differential privacy analysis [37]: Given two input tables D and D′ with d challenge rows, we create d−1 intermediate input tables Di, such that D and D1, Dd−1 and D ′ and Di and Di+1 are adjacent.”
MethodJansen, R., & Johnson, A. (2016) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/2976749.2978310 · Cited by 71
“Given ∆ f , the Gaussian mechanism using the bound for σ of Dwork et al. [12] is as follows: G satisfies ( (cid:101) , δ ) -differential privacy for (cid:101) , δ ≤ 1 [12].”
BackgroundMethodInfluentialDifferentially Private Learning with Kernels
Jain, P., & Thakurta, A. (2013) · Cited by 70
A New Framework for Privacy-Preserving Aggregation of Time-Series Data
Benhamouda, F., Jóye, M., & Libert, B. (2016) · ACM Transactions on Information and System Security · doi:10.1145/2873069 · Cited by 70
“In particular, although the focus of this paper is put on the encryption, the proposed schemes are compatible with the differential-privacy framework [Dwork 2008; Dwork et al. 2006].”
Dataflow Challenges in an Internet of Production: A Security & Privacy Perspective
Pennekamp, J., Henze, M., Schmidt, S., Niemietz, P., Fey, M., Trauth, D., Bergs, T., Brecher, C., & Wehrle, K. (2019) · doi:10.1145/3338499.3357357 · Cited by 77
“Third, anonymization approaches, such as k-anonymity [66], differential privacy [16], data aggregation [25, 61], and noise [15, 21],”
BackgroundPrivacy-preserving crowdsourced spectrum sensing
Jin, X., & Zhang, Y. (2016) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2016.7524588 · Cited by 69
“Approximate differential privacy relaxes on the strict requirement and allows a small additive term in the bound [33].”
BackgroundDifferentially private data aggregation with optimal utility
Eigner, F., Kate, A., Maffei, M., Pampaloni, F., & Pryvalov, I. (2014) · Annual Computer Security Applications Conference · doi:10.1145/2664243.2664263 · Cited by 69
“In particular, Dwork et al. [21] were the first to suggest the idea of employing secure multiparty computation (SMPC) to aggregate and perturb data in a privacy-preserving distributed manner.”
BackgroundPrivEx: Private Collection of Traffic Statistics for Anonymous Communication Networks
Elahi, T., Danezis, G., & Goldberg, I. (2014) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/2660267.2660280 · Cited by 70
“[10].”
BackgroundMethodInfluentialLarge-Scale Differentially Private BERT
Anil, R., Ghazi, B., Gupta, V., Kumar, R., & Manurangsi, P. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022 · doi:10.18653/v1/2022.findings-emnlp.484 · Cited by 68
Safeguarding cross-silo federated learning with local differential privacy
Wang, C., Wu, X., Liu, G., Deng, T., Peng, K., & Wan, S. (2021) · Digital Communications and Networks · doi:10.1016/j.dcan.2021.11.006 · Cited by 75
Differential Privacy on Finite Computers
Balcer, V., & Vadhan, S. (2019) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.679 · Cited by 80
Design of Privacy-Preserving Dynamic Controllers
Kawano, Y., & Cao, M. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.2994030 · Cited by 77
“In differential privacy analysis, this mapping is called a mechanism [17], [18].”
BackgroundMethodInfluentialFederated Heavy Hitters Discovery with Differential PrivacyPreprint
Zhu, W., Kairouz, P., McMahan, H. B., Sun, H., & Li, W. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.08534 · Cited by 73
Gupta, V., Jung, C., Neel, S., Roth, A., Sharifi-Malvajerdi, S., & Waites, C. (2021) · arXiv · doi:10.48550/arxiv.2106.04378 · Cited by 67
“Differentially private algorithms are robust to data-independent post-processing: Lemma 2.1 (Post-processing preserves DP [Dwork et al., 2006b]) .”
InfluentialAchieving Differentially Private Location Privacy in Edge-Assistant Connected Vehicles
Zhou, L., Yu, L., Du, S., Zhu, H., & Chen, C. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2876419 · Cited by 73
“notion of privacy, ( , δ)-DP [12], which means the privacy loss is bound by with a probability of at least 1 − δ.”
BackgroundMethodInfluentialMakris, I., Karampasi, A. S., Grammatikis, P. I. R., Episkopos, N., Iturbe, E., Rios, E., Piperigkos, N., Lalos, A. S., Xenakis, C., Λάγκας, Θ., et al. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2024.100717 · Cited by 74
Comparative Study of Differentially Private Data Synthesis Methods
Bowen, C. M., & Liu, F. (2020) · Statistical Science · doi:10.1214/19-sts742 · Cited by 87
“Differential Privacy (Dwork et al., 2006b): A sanitization algorithm R gives -DP if for all data sets (x,x′) that is d(x,x′) = 1, and all subsets Q ⊆ T∣∣∣∣log( Pr(R(s(x)) ∈ Q)Pr(R(s(x′)) ∈ Q) )∣∣∣∣ ≤ , (1) where T denotes the output range of the algorithm R, > 0 is the privacy budget (or loss), and…”
BackgroundInfluentialLower Bounds for Locally Private Estimation via Communication ComplexityPreprint
Duchi, J. C., & Rogers, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00582 · Cited by 109
“aints, in that our results apply to dierential privacy [13] and its weakenings, including concentrated dierential privacy [11,6], Renyi dierential privacy [26], and (";)-dierential privacy [12]. They also apply to arbitrarily interactive data release scenarios. Roughly, what we show is that so long as we wish to…”
BackgroundSecure multiparty aggregation with differential privacy: a comparative study
Goryczka, S., Xiong, L., & Sunderam, V. (2013) · Proceedings of the Joint EDBT/ICDT 2013 Workshops · doi:10.1145/2457317.2457343 · Cited by 64
“have developed distributed algorithms for random number generations, which shares are drawn from binomial and Poisson distributions [18].”
BackgroundPrivacy-aware regression modeling of participatory sensing data
Ahmadi, H., Pham, N., Ganti, R., Abdelzaher, T., Nath, S., & Han, J. (2010) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/1869983.1869994 · Cited by 76
“Finally, several recent works have proposed cryptographic solutions for privacy-preserving modeling or aggregation of distributed data [8, 15, 36].”
BackgroundEfficient Utility Improvement for Location Privacy
Chatzikokolakis, K., ElSalamouny, E., & Palamidessi, C. (2017) · Proceedings on Privacy Enhancing Technologies · doi:10.1515/popets-2017-0051 · Cited by 82
Privacy preserving classification on local differential privacy in data centers
Fan, W., He, J., Guo, M., Li, P., Han, Z., & Wang, R. (2019) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2019.09.009 · Cited by 66
Differentially Private Contextual Linear BanditsPreprint
Shariff, R., & Sheffet, O. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.00068 · Cited by 125
“Differential privacy, first introduced by Dwork et al. [17, 16], is a rigorous mathematical notion of privacy that requires the probability of any observable output to change very little when any single datum changes.”
BackgroundPrivacy-preserving point-of-interest recommendation based on geographical and social influence
Huo, Y., Chen, B., Tang, J., & Zeng, Y. (2020) · Information Sciences · doi:10.1016/j.ins.2020.07.046 · Cited by 68
“Thereby, we can obtain the global sensitivity ∆f of the query function according to Eq.”
BackgroundInfluentialDifferentially private cloud-based multi-agent optimization with constraints
Hale, M., & Egerstedty, M. (2015) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2015.7170902 · Cited by 78
“The notion of differential privacy was first established in the database literature as a way of providing strong practical guarantees of privacy to users contributing personal data to a database [5], [6].”
Background
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.