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 501–600 of 1,008
Differentially Private Query Release Through Adaptive ProjectionPreprint
Aydöre, S., Brown, W., Kearns, M. J., Kenthapadi, K., Melis, L., Roth, A., & Siva, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.06641 · Cited by 68
“For a dataset of size n , this results in error scaling as ˜ O √ [13].”
MethodInfluentialSelf-citationELXGB: An Efficient and Privacy-Preserving XGBoost for Vertical Federated Learning
Xu, W., Zhu, H., Zheng, Y., Wang, F., Zhao, J., Liu, Z., & Li, H. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3394706 · Cited by 32
“The definition of differential privacy [29] is as follows: Definition 1 (( (cid:5) , δ )-differential privacy): Given a randomized algorithm A , result ( A ) represents the set composed of all outputs of the algorithm.”
BackgroundTan, Z., See-To, E. W. K., Lee, K.-Y., Dai, H., & Wong, M. (2024) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2024.103996 · Cited by 37
Adaptive Multipersonalized Federated Learning for State of Health Estimation of Multiple Batteries
Wang, T., Dong, Z. Y., & Xiong, H. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3448626 · Cited by 36
Privacy-Preserving Financial Anomaly Detection via Federated Learning & Multi-Party Computation
Arora, S. S., Beams, A., Chatzigiannis, P., Meiser, S., Patel, K., Raghuraman, S., Rindal, P., Shah, H., Wang, Y., Wu, Y., et al. (2024) · Annual Computer Security Applications Conference Workshops (ACSAC Workshops) · doi:10.1109/acsacw65225.2024.00038 · Cited by 41
“See [14] for an efficient instantiation.”
Private Empirical Risk Minimization, Revisited.
Bassily, R., Smith, A., & Thakurta, A. (2014) · Cited by 31
Sphinx: Enabling Privacy-Preserving Online Learning over the Cloud
Han, T., Zeng, C., Ren, Z., Chai, D., Zhang, J., Chen, K., & Yang, Q. (2022) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp46214.2022.9833648 · Cited by 42
“Some other centralized training solutions adopt DP-based algorithms to protect privacy information by introducing randomization in the algorithm ([15]–[17], [19], [30]–[32]).”
BackgroundInteractive Proofs For Differentially Private Counting
Biswas, A., & Cormode, G. (2023) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3576915.3616681 · Cited by 34
“proposed using standard MPC for computing DP statistics [31].”
MethodDifferentially Private Exponential Random Graphs
Karwa, V., Slavković, A., & Krivitsky, P. N. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11257-2_12 · Cited by 31
“A basic algorithm for releasing the output of any function f under EDP uses the Laplace Mechanism (e.g., see Dwork et al. (2006b)).”
BackgroundMethodInfluentialInvestigating Statistical Privacy Frameworks from the Perspective of Hypothesis Testing
Liu, C., He, X., Chanyaswad, T., Wang, S., & Mittal, P. (2019) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2019-0045 · Cited by 31
Differentially Private Confidence Intervals for Empirical Risk Minimization
Wang, Y., Kifer, D., & Lee, J. (2019) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.660 · Cited by 31
An Improved Gap-Dependency Analysis of the Noisy Power MethodPreprint
Balcan, M.-F., Du, S. S., Wang, Y., & Yu, A. W. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.07046 · Cited by 31
“We are interested in algorithms that meet the following formal guarantees: Privacy guarantee We adopt the concept of ( ε, δ )-differential privacy proposed in [5].”
Local Private Hypothesis Testing: Chi-Square TestsPreprint
Gaboardi, M., & Rogers, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.07155 · Cited by 65
“Among the different approaches, differential privacy (Dwork et al., 2006b) is emerging as a viable solution: it provides strong privacy guarantees, and it allows to release accurate statistics.”
BackgroundSenate: A Maliciously-Secure MPC Platform for Collaborative AnalyticsPreprint
Poddar, R., Kalra, S., Yanai, A., Deng, R., Popa, R. A., & Hellerstein, J. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13752 · Cited by 46
“In principle, one can use a general-purpose MPC protocol to implement a given DP mechanism for computing noised queries in the standard model [27,29]—each party contributes a share of the randomness, which is combined within MPC to generate noise and perturb the query results, depending on the mechanism.”
MethodExplainable machine learning models with privacy
Bozorgpanah, A., & Torra, V. (2024) · Progress in Artificial Intelligence · doi:10.1007/s13748-024-00315-2 · Cited by 36
“Randomized response [29] and the Laplace distribution mechanism [30] are alternative data protection methods available in the literature.”
Privacy-Preserving State Estimation in the Presence of Eavesdroppers: A Survey
Yan, X., Zhou, G., Quevedo, D. E., Murguia, C., Chen, B., & Huang, H. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3440042 · Cited by 30
“Differential privacy (DP) is known as a classical perturbation method that was proposed by Dwork et al. in 2006 [61], [62].”
Differential Privacy by Typing in Security Protocols
Eigner, F., & Maffei, M. (2013) · IEEE Computer Security Foundations Workshop (CSFW) · doi:10.1109/csf.2013.25 · Cited by 30
“, verifiable secret sharing [6], secure function evaluations [7], secure multi-party computations [8], multi-party distributed data”
BackgroundPrivacy attacks against deep learning models and their countermeasures
Shafee, A. A., & Awaad, T. A. (2020) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2020.101940 · Cited by 34
Quantifying Membership Privacy via Information Leakage
Saeidian, S., Cervia, G., Oechtering, T. J., & Skoglund, M. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3073804 · Cited by 37
Local Differential Privacy Is Equivalent to Contraction of an $f$-Divergence
Asoodeh, S., Aliakbarpour, M., & Calmon, F. P. (2021) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit45174.2021.9517999 · Cited by 44
Network Traffic Shaping for Enhancing Privacy in IoT Systems
Xiong, S., Sarwate, A. D., & Mandayam, N. B. (2022) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2021.3140174 · Cited by 38
Behavior Privacy Preserving in RF Sensing
Liu, J., Xiao, C., Cui, K., Han, J., Xu, X., & Ren, K. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3143880 · Cited by 34
“To protect database privacy, Dwork et al. [42] add certain noise to the data.”
BackgroundOnline Experimentation: Benefits, Operational and Methodological Challenges, and Scaling Guide
Bojinov, I., & Gupta, S. (2022) · Harvard Data Science Review · doi:10.1162/99608f92.a579756e · Cited by 47
Differentially Private Release of Israel's National Registry of Live Births
Hod, S., & Canetti, R. (2025) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp61157.2025.00101 · Cited by 30
“A common blueprint for building a differentially private version of a function that takes a private dataset as input (e.g., count or mean) is to add sufficient random noise to the result [2], [37].”
Differentially private search log sanitization with optimal output utility
Hong, Y., Vaidya, J. S., Lu, H., & Wu, M. (2012) · International Conference on Extending Database Technology (EDBT) · doi:10.1145/2247596.2247604 · Cited by 30
“’s work [19] (indistinguishability differe ntial privacy [6]) by Götz et al.”
BackgroundPure Differential Privacy for Rectangle Queries via Private Partitions
Dwork, C., Naor, M., Reingold, O., & Rothblum, G. N. (2015) · Lecture notes in computer science · doi:10.1007/978-3-662-48800-3_30 · Cited by 58
Self-citationThat which we call privatePreprint
Erlingsson, Ú., Mironov, I., Raghunathan, A., & Song, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.03566 · Cited by 32
“The privacy of ML models trained by iterative DP-SGD with clipping and Gaussian noise [1] can be analyzed via naı̈ve [6] or advanced [8] composition theorems.”
MethodSelf-citationPrivacy preserving and secure robust federated learning: A survey
Han, Q., Lu, S., Wang, W., Qu, H., Li, J., & Gao, Y. (2024) · Concurrency and Computation: Practice and Experience · doi:10.1002/cpe.8084 · Cited by 29
“DP 28,29 is a technique that protects users’ personal privacy information by perturbing the data with well-designed noise, which allows the data to maintain their original distribution characteristics in a way that supports model training while ensuring data utility to an extent.”
BackgroundPrivacy-Preserving Deep Learning Based Record Linkage
Ranbaduge, T., Vatsalan, D., & Ding, M. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3342757 · Cited by 29
“Definition 2 (Differential Privacy [26]): A randomised al-gorithm A is (cid:2) -differentially private if for all neighbouring where Pr [ · ] denotes the probability of an event.”
BackgroundThe Privacy of the Analyst and the Power of the State
Dwork, C., Naor, M., & Vadhan, S. (2012) · Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2012.87 · Cited by 36
“1Exceptions include [9] and all work in the local model [10].”
BackgroundSelf-citationPrivacy-Preserving Cost-Sensitive Learning
Yang, Y., Huang, S., Huang, W. W., & Chang, X. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2996972 · Cited by 38
“Definition 2 ( ε -Differential Privacy[11], [27]): A randomized algorithm A gives ε -differential privacy if for any neighboring data sets of D and D differing only on a single entry, and for all S ⊆ Range( A ), where A ( D ) (resp.”
BackgroundSentence-level Privacy for Document Embeddings
Meehan, C., Mrini, K., & Chaudhuri, K. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.238 · Cited by 51
Secure multi-party differential privacy
Kairouz, P., Oh, S., & Viswanath, P. (2015) · neural information processing systems · Cited by 57
On learning cluster coefficient of private networks
Wang, Y., Wu, X., Zhu, J., & Xiang, Y. (2013) · Social Network Analysis and Mining · doi:10.1007/s13278-013-0127-7 · Cited by 29
Secure Multi-party Computation for Cloud-Based Control
Alexandru, A. B., & Pappas, G. J. (2019) · Springer eBooks · doi:10.1007/978-981-15-0493-8_9 · Cited by 29
GAN-DP: Generative Adversarial Net Driven Differentially Privacy-Preserving Big Data Publishing
Qu, Y., Yu, S., Zhang, J., Bình, H. T. T., Gao, L., & Zhou, W. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8761070 · Cited by 31
“It provides solid theoretical foundation to privacy protection [12] [13].”
BackgroundTechniques, Taxonomy, and Challenges of Privacy Protection in the Smart Grid
Uludag, S., Zeadally, S., & Badra, M. (2015) · Computer communications and networks · doi:10.1007/978-3-319-08470-1_15 · Cited by 32
“The notion of differential privacy is coined in [49] and [50].”
BackgroundThe Large Margin Mechanism for Differentially Private MaximizationPreprint
Chaudhuri, K., Hsu, D., & Song, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.2177 · Cited by 38
“The following definitions of (approximate) differential privacy are from [17] and [20].”
BackgroundDifferentially Private k-Means with Constant Multiplicative ErrorPreprint
Kaplan, H. Y., & Stemmer, U. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.08001 · Cited by 68
“hanism A that on input S 2 U n outputs f (S ) + Lap( " ) d is ("; 0) - dierentially private. Moreover, Pr h kA (S ) f (S )k1 > i d exp " : Theorem 2.6 (Gaussian Mechanism [19]) . Let "; 2 (0 ;1) , and assume f : U n ! R d has L 2 - sensitivity . Let " p 2ln(1 :25 = ). The mechanism that on…”
BackgroundInfluentialvan Dijk, M., Nguyen, N. V., Nguyen, T. N., Nguyen, L. M., Tran-Dinh, Q., & Nguyen, P. H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.09208 · Cited by 33
“Differential privacy [Dwork et al., 2006b, Dwork, 2011, Dwork et al., 2014, 2006a] defines privacy guarantees for algorithms on databases, in our case a client’s sequence of mini-batch gradient computations on his/her training data set.”
BackgroundLeveraging Public Data for Practical Private Query ReleasePreprint
Liu, T., Vietri, G., Steinke, T., Ullman, J., & Wu, Z. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08598 · Cited by 29
“Differential privacy (Dwork et al., 2006b) is a rigorous criterion that provides meaningful guarantees of individual privacy while allowing for trade-offs between privacy and accuracy.”
BackgroundMethodInfluentialA survey of the fusion of traditional data security technology and blockchain
Xu, Y., Xu, G., Liu, Y., Liu, Y., & Shen, M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124151 · Cited by 31
Differential Privacy in Practice
Nguyen, H. H., Kim, J. K., & Kim, Y.-H. (2013) · Journal of Computing Science and Engineering · doi:10.5626/jcse.2013.7.3.177 · Cited by 28
“(Gaussian mechanism [6]) For any function f : D → R the mechanism”
BackgroundThe Challenges of Effectively Anonymizing Network Data
Coull, S. E., Monrose, F., Reiter, M. K., & Bailey, M. (2009) · Cybersecurity Applications & Technology Conference for Homeland Security (CATCH) · doi:10.1109/catch.2009.27 · Cited by 28
“As an example, average salary information for a given area should remain unchanged, but it should not be possible to infer a specific person’s salary.”
BackgroundAchieving Secure and Differentially Private Computations in Multiparty Settings
Acar, A., Celik, Z. B., Aksu, H., Uluagac, A. S., & McDaniel, P. D. (2017) · IEEE Symposium on Privacy-Aware Computing (PAC) · doi:10.1109/pac.2017.12 · Cited by 28
“Preserving the privacy of the users and data is a longstudied problem in the area of cryptography [16], [18], [22], [30], [34], [35].”
BackgroundRON-Gauss: Enhancing Utility in Non-Interactive Private Data Release
Chanyaswad, T., Liu, C., & Mittal, P. (2018) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2019-0003 · Cited by 32
“There is also the ( , δ)-differential privacy (( , δ)-DP) [30, 37], which is a relaxation of this definition.”
Securely Sampling Biased Coins with Applications to Differential Privacy
Champion, J., Shelat, A. A., & Ullman, J. (2019) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3319535.3354256 · Cited by 28
“[14] and has many follow-up works [2, 3, 11, 17, 34].”
BackgroundMethodInfluentialDifferentially Private Release of Datasets using Gaussian Copula
Asghar, H. J., Ding, M., Rakotoarivelo, T., Mrabet, S., & Kâafar, M. A. (2020) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.686 · Cited by 28
Limits of Private Learning with Access to Public DataPreprint
Alon, N., Bassily, R., & Moran, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11519 · Cited by 43
Differentially Private Federated Bayesian Optimization with Distributed ExplorationPreprint
Dai, Z., Low, B. K. H., & Jaillet, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.14153 · Cited by 52
“In particular, privacy preservation using DP has been an important topic for FL [27, 41, 62, 65], including both central DP (with trusted central server) [47] and local [32, 64, 70] or distributed DP [4, 6, 18, 58] (without trusted central server).”
BackgroundThe Price of Differential Privacy under Continual ObservationPreprint
Jain, P., Raskhodnikova, S., Sivakumar, S., & Smith, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.00828 · Cited by 28
“2 (Batch Model of Differential Privacy [10, 9]).”
BackgroundMethodInfluentialA Comprehensive Survey on Privacy Preservation Algorithms in Data Mining
Kiran, A., & Vasumathi, D. (2017) · IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) · doi:10.1109/iccic.2017.8524294 · Cited by 30
“Noise Addition Technique Noise addition technique is a popular and most widely used data modification technique, in which data privacy is maintained by adding some information (Noise) to the original sensitive information [22][23].”
MethodKserawi, F., Al-Marri, S. M., & Malluhi, Q. M. (2022) · IEEE Access · doi:10.1109/access.2022.3167015 · Cited by 27
“If those trusted aggregators and service providers are no longer trusted, a distributed differential privacy approach [46] can be adopted.”
BackgroundDifferentially Private K-Means Clustering Applied to Meter Data Analysis and Synthesis
Ravi, N., Scaglione, A., Kadam, S., Gentz, R., Peisert, S., Lunghino, B., Levijarvi, E., & Shumavon, A. (2022) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2022.3184252 · Cited by 27
“The first and the most widespread definition of differential privacy was introduced in [15], [28].”
BackgroundDynamic routing approach for enhancing source location privacy in wireless sensor networks
Kumar, G., Rathore, R. S., Thakur, K., Almadhor, A. S., Biabani, S. A. A., & Chander, S. (2023) · Wireless Networks · doi:10.1007/s11276-023-03322-8 · Cited by 27
“Differential privacy methods have been developed using privacy matrix factorization algorithms [39, 40].”
MethodDistributional differential privacy for large-scale smart metering
Jelasity, M., & Birman, K. (2014) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/2600918.2600919 · Cited by 27
“For the present paper, details of the distributed communication are irrelevant to the analysis: instead, we assume that there is a secure privacy preserving mechanism in place to compute the sum query of the readings, such as those discussed in [11, 12].”
BackgroundInfluentialA Privacy-Preserving Health Data Aggregation Scheme
Liu, Y., Liu, G., Chi, C., Xia, Z., & Shen, J. (2016) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2016.08.023 · Cited by 27
pMSE Mechanism: Differentially Private Synthetic Data with Maximal Distributional Similarity
Snoke, J., & Slavković, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-99771-1_10 · Cited by 41
“In this case private parameters are drawn from posterior distribution f ( θ | s ∗ ) where s is the Bayesian sufficient statistic and s ∗ is the statistic perturbed according to the Laplace mechanism (e.g., see Dwork et al. (2006)).”
BackgroundMethodInfluentialOrder-Revealing Encryption and the Hardness of Private Learning
Bun, M., & Zhandry, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-662-49096-9_8 · Cited by 34
“The definition with positive δ, called approximate differential privacy, first appeared in [19] and has since been shown to enable substantial accuracy gains.”
BackgroundIncentive Compatible Privacy-Preserving Distributed Classification
Nix, R., & Kantarciouglu, M. (2011) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2011.52 · Cited by 27
“[38], noise addition techniques [15], [9], and cryptographic”
BackgroundDifferentially private Kalman filtering
Ny, J. L., & Pappas, G. J. (2012) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2012.6483414 · Cited by 27
Privacy and Utility Tradeoff in Approximate Differential PrivacyPreprint
Geng, Q., Ding, W., Guo, R., & Kumar, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.00877 · Cited by 30
“Definition 1 (( , δ)-differential privacy (Dwork et al., 2006a)).”
BackgroundPrivacy-preserving Learning via Deep Net PruningPreprint
Huang, Y., Su, Y., Ravi, S., Song, Z., Arora, S., & Li, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01876 · Cited by 29
Information-Theoretic Generalization Bounds for Stochastic Gradient DescentPreprint
Neu, G., Dziugaite, G. K., Haghifam, M., & Roy, D. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00931 · Cited by 118
Federated $f$-Differential PrivacyPreprint
Zheng, Q., Chen, S., Long, Q., & Su, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11158 · Cited by 37
“The most popular statistical privacy definition to date is ( (cid:15), δ )-differential privacy [DKM + 06, DMNS06].”
BackgroundOn the Power of Multiple Anonymous Messages
Ghazi, B., Golowich, N., Kumar, R., Pagh, R., & Velingker, A. (2019) · arXiv · doi:10.48550/arxiv.1908.11358 · Cited by 26
Modular control under privacy protection: Fundamental trade-offs
Kawano, Y., Kashima, K., & Cao, M. (2021) · Automatica · doi:10.1016/j.automatica.2021.109518 · Cited by 26
Designing statistical privacy for your data
Machanavajjhala, A., & Kifer, D. (2015) · Communications of the ACM · doi:10.1145/2660766 · Cited by 26
The Geometry of Differential Privacy: The Small Database and Approximate Cases
Nikolov, A., Talwar, K., & Zhang, L. (2016) · SIAM Journal on Computing · doi:10.1137/130938943 · Cited by 26
Testing the Lipschitz Property over Product Distributions with Applications to Data Privacy
Dixit, K., Jha, M. K., Raskhodnikova, S., & Thakurta, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-36594-2_24 · Cited by 26
Differentially Private Kalman Filtering
Ny, J. L. (2020) · Springer briefs in electrical and computer engineering · doi:10.1007/978-3-030-41039-1_5 · Cited by 26
Private Approximations of the 2nd-Moment Matrix Using Existing Techniques in Linear RegressionPreprint
Sheffet, O. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.00056 · Cited by 26
Private False Discovery Rate ControlPreprint
Dwork, C., Su, W., & Zhang, L. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.03803 · Cited by 26
“Definition 2.2 (Differential privacy [10, 9]) .”
InfluentialSelf-citationAntipodes of Label Differential Privacy: PATE and ALIBIPreprint
Esmaeili, M. M., Mironov, I., Prasad, K., Shilov, I., & Tramèr, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03408 · Cited by 57
“Their noise distributions are calibrated to the function’s sensitivity—the maximal distance between the function’s outputs on adjacent inputs (D and D′ in Definition 2.1) under the `1 or `2 metrics for the Laplace and Gaussian mechanisms respectively.”
BackgroundInfluentialSelf-citationPrivacy Implications of Retrieval-Based Language Models
Huang, Y., Gupta, S., Zhong, Z., Li, K., & Chen, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.921 · Cited by 25
“Privacy-preserving quantum machine learning using differential privacy,”
Senekane, M., Mafu, M., & Taele, B. M. (2017) · 2017 IEEE AFRICON · doi:10.1109/afrcon.2017.8095692 · Cited by 25
“A mechanism that is used to guarantee security in such cases is differential privacy [9], [10], [11].”
BackgroundPreserving differential privacy under finite-precision semantics
Gazeau, I., Miller, D., & Catuscia Palamidessi, A. (2016) · Theoretical Computer Science · doi:10.1016/j.tcs.2016.01.015 · Cited by 25
SPEED: secure, PrivatE, and efficient deep learning
Sébert, A. G., Pinot, R., Zuber, M., Gouy‐Pailler, C., & Sirdey, R. (2021) · Machine Learning · doi:10.1007/s10994-021-05970-3 · Cited by 34
“1 Differential privacy Differential privacy [37] is a gold standard concept in privacy preserving data analysis.”
BackgroundTableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing
Hu, A., Xie, R., Lü, Z., Hu, A., & Xue, M. (2021) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3460120.3485251 · Cited by 25
“The accumulation of multiple Gaussian noise addition [11] relies on privacy accountant techniques [1] and Rényi differential privacy [31].”
MethodZhou, W., Zhu, T., Ye, D., Ren, W., & Choo, K. R. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3312118 · Cited by 30
“…can be expressed as Note that the classical definition of pure differential privacy does not include the additional parameter δ , Dwork et al. [40] was the first to propose approximate differential privacy, which involves the parameter δ , where δ is the probability that pure differential…”
BackgroundEfficient and Privacy-Preserving Feature Importance-Based Vertical Federated Learning
Li, A., Huang, J., Jia, J., Peng, H., Zhang, L., Tuan, L. A., Yu, H., & Li, X. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3333879 · Cited by 25
“…R satisfies ( (cid:2), δ )-DP if for any subset of outputs S ⊆ R and for any two adjacent inputs d, d (cid:4) ∈ D , ( Instead of the original definition of (cid:2) -DP, we adopt the variant [37] which allows for the possibility that plain (cid:2) -differential privacy is broken with probability δ .”
MethodPrivate Convex Optimization via Exponential Mechanism
Gopi, S., Lee, Y. T., & Liu, D. (2024) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.869 · Cited by 25
Optimizing Batch Linear Queries under Exact and Approximate Differential Privacy
Yuan, G., Zhang, Z., Winslett, M., Xiao, X., Yang, Y., & Hao, Z. (2015) · ACM Transactions on Database Systems · doi:10.1145/2699501 · Cited by 25
Differentially Private Analysis of Outliers
Okada, R., Fukuchi, K., & Sakuma, J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23525-7_28 · Cited by 25
“(1) provides ( , δ)differential privacy [2]: Aq(X) = q(X) + Y, (1)”
Real-time privacy-preserving model-based estimation of traffic flows
Ny, J. L., Touati, A., & Pappas, G. J. (2014) · ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS) · doi:10.1109/iccps.2014.6843714 · Cited by 25
On differentially private Kalman filtering
Degue, K. H., & Ny, J. L. (2017) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2017.8308690 · Cited by 25
“The Gaussian mechanism [5] consists in adding Gaussian noise proportional to the `2-sensitivity to provide ( , δ)differential privacy.”
BackgroundPriPeARL: A Framework for Privacy-Preserving Analytics and Reporting at LinkedIn
Kenthapadi, K., & Tran, T. T. L. (2018) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3269206.3272031 · Cited by 40
“Our approach modifies the reported aggregate counts using a random noise addition mechanism, inspired by differential privacy [7, 8].”
MethodSelf-citationLimits of Computational Differential Privacy in the Client/Server Setting
Groce, A., Katz, J. I., & Yerukhimovich, A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19571-6_25 · Cited by 25
Assisted Learning: A Framework for Multi-Organization LearningPreprint
Xian, X., Wang, X., Ding, J., & Ghanadan, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.00566 · Cited by 32
On Distributed Differential Privacy and Counting Distinct Elements
Chen, L., Ghazi, B., Kumar, R., & Manurangsi, P. (2020) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itcs.2021.56 · Cited by 28
Privacy-Preserving Dynamic Personalized Pricing with Demand LearningPreprint
Chen, X., Simchi‐Levi, D., & Wang, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.12920 · Cited by 27
“Differential privacy is a mathematically rigorous measure of privacy protection and has been extensively studied and applied since its proposal in the work of Dwork et al. (2006b).”
BackgroundInfluentialNon-Euclidean Differentially Private Stochastic Convex Optimization: Optimal Rates in Linear Time
Bassily, R., Guzmán, C., & Nandi, A. (2021) · University of Twente Research Information · doi:10.48550/arxiv.2103.01278 · Cited by 55
“Definition 2.2 (Differential Privacy [16, 17, 18]) .”
InfluentialIntegrating Technical and Legal Concepts of Privacy
Sokolovska, A., & Kocarev, L. (2018) · IEEE Access · doi:10.1109/access.2018.2836184 · Cited by 24
“A relaxation of differential privacy is approximate or ( (cid:15), δ )-differential privacy [67], which essentially guarantees that the probability that any individual suffers privacy loss exceeding (cid:15) is bounded by δ .”
BackgroundLocal dampening: differential privacy for non-numeric queries via local sensitivity
Farias, V. A. E., Brito, F. T., Flynn, C. J., Machado, J. C., Majumdar, S., & Srivastava, D. (2023) · The VLDB Journal · doi:10.1007/s00778-022-00774-w · Cited by 24
“(ε-Differential Privacy [7, 8]).”
Beyond federated learning: On confidentiality-critical machine learning applications in industry
Zellinger, W., Wieser, V., Kumar, M., Brunner, D. J., Shepeleva, N., Gálvez, R., Langer, J., Fischer, L., & Moser, B. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.01.296 · Cited by 29
Comparing Local and Central Differential Privacy Using Membership Inference Attacks
Bernau, D., Robl, J., Grassal, P. W., Schneider, S., & Kerschbaum, F. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-81242-3_2 · Cited by 33
Topology-Aware Differential Privacy for Decentralized Image Classification
Guo, S., Zhang, T., Xu, G., Yu, H., Xiang, T., & Liu, Y. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3105723 · Cited by 32
“According to the Gaussian mechanism [14], the update rule in Line 19 is ( i , δi )-DP at one iteration if we choose”
BackgroundMethodDistribution-invariant differential privacy
Bi, X., & Shen, X. (2022) · Journal of Econometrics · doi:10.1016/j.jeconom.2022.05.004 · Cited by 35
Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms
Hallaji, E., Razavi‐Far, R., & Saif, M. (2022) · Adaptation, learning, and optimization · doi:10.1007/978-3-031-11748-0_3 · Cited by 31
“On the other hand, local [24] and distributed DP [11, 25] both assume that the aggregator is not trusted, which perfectly complies with the FDL paradigm.”
BackgroundWidespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix It
Casacuberta, S., Shoemate, M., Vadhan, S., & Wagaman, C. (2022) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3548606.3560708 · Cited by 24
“For measuring the closeness of the probability distributions M(u) andM(u′), we use the standard definition of (ε, δ)-differential privacy [13], requiring that:”
Method
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.