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 101–200 of 1,008
Differentially private filtering
Le Ny, J., & Pappas, G. J. (2012) · 2012 IEEE 51st IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2012.6426355 · Cited by 188
“We refer the reader to the surveys by Dwork, e.g., [17], for additional background on differential privacy.”
BackgroundMethodPrivate analysis of graph structure
Karwa, V., Raskhodnikova, S., Smith, A., & Yaroslavtsev, G. (2011) · Proceedings of the VLDB Endowment · doi:10.14778/3402707.3402749 · Cited by 199
“( Differential Privacy, [4, 2]) Let (cid:4) and δ be small constants.”
BackgroundDecentralized federated learning through proxy model sharing
Kalra, S., Wen, J., Cresswell, J. C., Volkovs, M., & Tizhoosh, H. R. (2023) · Nature Communications · doi:10.1038/s41467-023-38569-4 · Cited by 160
“(7) is based on the Gaussian mechanism [Dwork et al., 2006a] which meets the requirement of Eq.”
BackgroundAnalyze gauss: optimal bounds for privacy-preserving principal component analysis
Dwork, C., Talwar, K., Thakurta, A., & Zhang, L. (2014) · Proceedings of the forty-sixth annual ACM symposium on Theory of computing · doi:10.1145/2591796.2591883 · Cited by 173
“Specifically, we will use the Gaussian mechanism [12], which adds independently chosen Gaussian noise to each entry of AA.”
MethodSelf-citationDifferentially private Naive Bayes learning over multiple data sources
Li, T., Li, J., Liu, Z., Li, P., & Jia, C. (2018) · Information Sciences · doi:10.1016/j.ins.2018.02.056 · Cited by 190
Deep Learning with Gaussian Differential Privacy
Bu, Z., Dong, J., Long, Q., & Weijie, S. (2020) · Harvard Data Science Review · doi:10.1162/99608f92.cfc5dd25 · Cited by 164
The Optimal Noise-Adding Mechanism in Differential Privacy
Geng, Q., & Viswanath, P. (2016) · IEEE Transactions on Information Theory · doi:10.1109/tit.2015.2504967 · Cited by 169
Differential privacy-enabled federated learning for sensitive health data
Choudhury, O., Gkoulalas-Divanis, A., Salonidis, T., Sylla, I., Park, Y., Hsu, G., & Das, A. (2019) · arXiv · doi:10.48550/arxiv.1910.02578 · Cited by 184
“Although state-of-the-art approaches to address such attacks are based on differential privacy [20], their performance has not been investigated for healthcare applications.”
BackgroundAdversary Instantiation: Lower Bounds for Differentially Private Machine Learning
Nasr, M., Songi, S., Thakurta, A., Papernot, N., & Carlin, N. (2021) · 2021 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp40001.2021.00069 · Cited by 135
“Differential privacy (DP) [14, 16, 17] has become the defacto definition of algorithmic privacy.”
BackgroundPrivate Convex Empirical Risk Minimization and High-dimensional Regression
Kifer, D., Smith, A., & Thakurta, A. (2012) · Cited by 180
Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget
Lee, J., & Kifer, D. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3220076 · Cited by 165
“, pure differential privacy [8], approximate differential privacy [7], or zero-mean concentrated differential privacy [4]).”
BackgroundDifferentially Private Learning Needs Better Features (or Much More Data)
Tramèr, F., & Boneh, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.11660 · Cited by 77
“…observation that model gradients lie in a low-dimensional subspace (Kairouz et al., 2020; Zhou et al., 2020b). satisfies (ε, δ)-differential privacy (Dwork et al., 2006a), if for any datasets D,D′ that differ in one record, and any set of models S: Pr[A(D) ∈ S] ≤ eε Pr[A(D′) ∈ S] + δ. DP bounds…”
BackgroundMethodOn the Relation Between Identifiability, Differential Privacy, and Mutual-Information Privacy
Wang, W., Ying, L., & Zhang, J. (2016) · IEEE Transactions on Information Theory · doi:10.1109/tit.2016.2584610 · Cited by 169
“Differential privacy, as an emerging analytical foundation for privacy-preserving data analysis, was developed by a line of work [1]–[3], and since then both interactive model (e.g., [1], [4]–[9]) and non-interactive model (e.g., [8], [10]–[15]) have been studied in the literature.”
BackgroundMembership Inference Attack against Differentially Private Deep Learning Model.
Rahman, M. A., Rahman, T., Laganière, R., & Mohammed, N. (2018) · Cited by 292
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
Ponomareva, N., Hazimeh, H., Kurakin, A., Xu, Z., Denison, C., McMahan, H. B., Vassilvitskii, S., Chien, S., & Thakurta, A. G. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14649 · Cited by 166
“Distributed DP seeks to recover the utility of central DP without having to rely on a fully trusted central aggregator (Dwork et al., 2006; Bittau et al., 2017; Kairouz et al., 2021b; Agarwal et al., 2021).”
BackgroundInfluentialPrivacy-Preserving Aggregation in Federated Learning: A Survey
Liu, Z., Guo, J., Yang, W., Fan, J., Lam, K., & Zhao, J. (2022) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2022.3190835 · Cited by 259
Distributed Private Data Analysis: Simultaneously Solving How and What
Beimel, A., Kobbi Nissim, B., & Omri, E. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85174-5_25 · Cited by 163
Individual Differential Privacy: A Utility-Preserving Formulation of Differential Privacy Guarantees
Soria-Comas, J., Domingo-Ferrer, J., Sanchez, D., & Megias, D. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2663337 · Cited by 160
“onare[21,22]. In[23],a differentiallyprivatealternativetotheID3algorithmforlearningdecisiontrees isproposed. Thesecondlineofresearch,focusedonfindingrelaxationsofDP,hasbeenactivesincetheinceptionofDP.In[24],theconceptofδ-approximate-indistinguishability is presented (a.k.a. (,δ)-indistinguishability in [11]). This relax…”
BackgroundThe Johnson-Lindenstrauss Transform Itself Preserves Differential Privacy
Blocki, J., Blum, A., Datta, A., & Sheffet, O. (2012) · 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2012.67 · Cited by 136
“Algorithm 1: Outputting the Laplacian of a Graph while Preserving Differential Privacy , and w = √ 2 , whose entries are iid samples of N (0 , 1).”
On syntactic anonymity and differential privacy
Clifton, C., & Tassa, T. (2013) · 2013 IEEE 29th International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew.2013.6547433 · Cited by 152
“(The additive noise δ in ( , δ)-indistinguishability does not necessarily provide the same protection and must be used carefully, see [20].”
BackgroundFast-adapting and privacy-preserving federated recommender system
Wang, Q., Yin, H., Chen, T., Yu, J., Zhou, A., & Zhang, X. (2022) · The VLDB Journal · doi:10.1007/s00778-021-00700-6 · Cited by 145
“We present DP-PrivRec, an extension of PrivRec, to strengthen our FL-based recommender with differential privacy (DP) [1,16,17,89].”
MethodOn the 'Semantics' of Differential Privacy: A Bayesian Formulation
Kasiviswanathan, S. P., & Smith, A. (2014) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.v6i1.634 · Cited by 156
“The schemes in all those papers, however, satisfy the following relaxation (first formulated by Dwork, Kenthapadi, McSherry, Mironov, and Naor [6]): Definition 1.”
BackgroundResultInfluentialAchieving differential privacy of data disclosure in the smart grid
Zhao, J. Y., Jung, T., Wang, Y., & Li, X. (2014) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2014.6847974 · Cited by 155
“In this paper, we investigate the privacy issues of the smart meters in the differential privacy context, which is originally proposed by Dwork et al. [15]–[17] as a privacy measure for database queries.”
AdaCliP: Adaptive Clipping for Private SGD
Pichapati, V., Suresh, A. T., Yu, F. X., Reddi, S. J., & Kumar, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07643 · Cited by 60
“We first formally describe differential privacy [17] and the previous differentially private SGD methods.”
MethodGeneralization in Adaptive Data Analysis and Holdout Reuse
Dwork, C., Feldman, V., Hardt, M., Pitassi, T., Reingold, O., & Roth, A. (2015) · arXiv · doi:10.48550/arxiv.1506.02629 · Cited by 152
“[9, 8] A randomized algorithm A with domain X for n > 0 is (ε, δ)-differentially private if for all pairs of datasets that differ in a single element S, S′ ∈ X: D ∞(A(S)‖A(S)) ≤ log(e).”
BackgroundSelf-citationGeneralized Gaussian Mechanism for Differential Privacy
Liu, F. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2845388 · Cited by 139
“(1), there are softer versions of DP, including the ð ; dÞ-approximate DP [13], the ð ; dÞ-probabilistic DP [14], the ð ; dÞ-random DP (rDP) [15], and the ð ; tÞ-concentrated DP (cDP) [16].”
BackgroundPrivacy Preserving Synthetic Data Release Using Deep Learning
Abay, N. C., Zhou, Y., Kantarcıoğlu, M., Thuraisingham, B., & Sweeney, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-10925-7_31 · Cited by 223
“1), as specified in the sequential composition theorem [10].”
BackgroundGraph Data Anonymization, De-Anonymization Attacks, and De-Anonymizability Quantification: A Survey
Ji, S., Mittal, P., & Beyah, R. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2016.2633620 · Cited by 141
“[133], [134], is another popular anonymization technique to provide a provable strong privacy guarantee.”
BackgroundRobust Traceability from Trace Amounts
Dwork, C., Smith, A., Steinke, T., Ullman, J., & Vadhan, S. (2015) · 2015 IEEE 56th Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2015.46 · Cited by 137
Self-citationDifferentially Private Online LearningPreprint
Jain, P., Kothari, P. K., & Thakurta, A. (2012) · Cited by 149
A Comprehensive Comparison of Multiparty Secure Additions with Differential Privacy
Goryczka, S., & Xiong, L. (2017) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2015.2484326 · Cited by 139
“Privacy of data subjects is protected if any data recipient does not learn anything about them including their participation in the data collection.”
BackgroundMethodInfluentialPrivacy-Preserving Data Publishing
Chen, B.-C., Kifer, D., LeFevre, K., & Machanavajjhala, A. (2009) · Foundations and Trends in Databases · doi:10.1561/1900000008 · Cited by 184
“Variants of differential privacy have been discussed in [49, 86, 167].”
BackgroundThe matrix mechanism: optimizing linear counting queries under differential privacy
Li, C., Miklau, G., Hay, M., McGregor, A., & Rastogi, V. (2015) · The VLDB Journal · doi:10.1007/s00778-015-0398-x · Cited by 146
“Approximate ( , δ)-differential privacy can be achieved by adding Gaussian noise calibrated to the L2 sensitivity of the queries [10,22].”
BackgroundMethodInfluentialDesfontaines, D., & Pejó, B. (2020) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2020-0028 · Cited by 211
Applications of Differential Privacy in Social Network Analysis: A Survey
Jiang, H., Pei, J., Yu, D., Yu, J., Gong, B., & Cheng, X. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3073062 · Cited by 193
“Definition 2 (Approximate differential privacy [30]).”
The Staircase Mechanism in Differential Privacy
Geng, Q., Kairouz, P., Oh, S., & Viswanath, P. (2015) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2015.2425831 · Cited by 140
Towards Practical Differentially Private Convex Optimization
Iyengar, R., Near, J. P., Song, D., Thakkar, O., Thakurta, A., & Wang, L. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00001 · Cited by 129
“To prevent such information leakage, differential privacy (DP) [4], [5] has been recently used as a gold standard for performing learning tasks over sensitive data.”
MethodInfluentialA Scalable Scheme for Privacy-Preserving Aggregation of Time-Series Data
Jóye, M., & Libert, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39884-1_10 · Cited by 143
“In particular, although the focus of this paper is put on the encryption, the proposed scheme is compatible with the differential-privacy framework [13, 12].”
Privacy Preserving Social Network Data Publication
Abawajy, J., Ninggal, M. I. H., & Herawan, T. (2016) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2016.2533668 · Cited by 143
Differential Privacy Preservation in Deep Learning: Challenges, Opportunities and Solutions
Zhao, J., Chen, Y., & Zhang, W. (2019) · IEEE Access · doi:10.1109/access.2019.2909559 · Cited by 134
“The additional variant δ, introduced in [34], allows for the possibility that plain ε-differential privacy is broken with probability δ, which is preferably smaller than 1/|d |.”
BackgroundReconstructing Training Data with Informed Adversaries
Balle, B., Cherubin, G., & Hayes, J. (2022) · 2022 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp46214.2022.9833677 · Cited by 83
Anonymization: The imperfect science of using data while preserving privacy
Gadotti, A., Rocher, L., Houssiau, F., Creţu, A.-M., & de Montjoye, Y.-A. (2024) · Science Advances · doi:10.1126/sciadv.adn7053 · Cited by 182
“Another popular relaxation is approximate differential privacy [also known as ( ε , δ )- differential privacy], which allows for a slightly larger privacy loss than the original one, with the allowed margin depending on the delta parameter ( 237 ).”
BackgroundPrivacy-Preserving Data Publishing
Chen, B.-C., Kifer, D., LeFevre, K., & Machanavajjhala, A. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982773 · Cited by 151
Resilient consensus for multi-agent systems subject to differential privacy requirements
Fiore, D., & Russo, G. (2019) · Automatica · doi:10.1016/j.automatica.2019.04.029 · Cited by 137
Composable and versatile privacy via truncated CDP
Bun, M., Dwork, C., Rothblum, G. N., & Steinke, T. (2018) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/3188745.3188946 · Cited by 201
“A popular relaxation, “approximate” or (ε , δ )-differential privacy [10], roughly guarantees that with probability at least 1 − δ the privacy loss does not exceed ε .”
BackgroundSelf-citationDetecting Violations of Differential Privacy
Ding, Z., Wang, Y., Wang, G., Zhang, D., & Kifer, D. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243818 · Cited by 103
“The term differential privacy covers a family of privacy definitions that include pure ε-differential privacy (the topic of this paper) [17] and its relaxations: approximate (ε,δ )differential privacy [16], concentrated differential privacy [8, 20], and Renyi differential privacy [31].”
BackgroundManipulation Attacks in Local Differential Privacy
Cheu, A., Smith, A., & Ullman, J. (2021) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp40001.2021.00001 · Cited by 161
Human-Factor-Aware Privacy-Preserving Aggregation in Smart Grid
Jia, W., Zhu, H., Cao, Z., Dong, X., & Xiao, C. (2014) · IEEE Systems Journal · doi:10.1109/jsyst.2013.2260937 · Cited by 137
“The use of binomial distribution first appeared in Dwork et al. [20].”
BackgroundMethodPrivacy via the Johnson-Lindenstrauss Transform
Kenthapadi, K., Korolova, A., Mironov, I., & Mishra, N. (2013) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.v5i1.625 · Cited by 108
Self-citationShielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection
Zhao, L., Hu, S., Wang, Q., Jiang, J., Chao, S., Luo, X., & Hu, P. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2020.2986205 · Cited by 127
The Limits of Two-Party Differential Privacy
McGregor, A., Mironov, I., Pitassi, T., Reingold, O., Talwar, K., & Vadhan, S. (2010) · 2010 IEEE 51st Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2010.14 · Cited by 119
Self-citationPublishing Search Logs—A Comparative Study of Privacy Guarantees
Götz, M., Machanavajjhala, A., Wang, G., Xiao, X., & Gehrke, J. E. (2011) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2011.26 · Cited by 143
“We define the phquery histogram, the phquery pair histogram, and the phclick histogram analogously.”
BackgroundMethodProbabilistic relational reasoning for differential privacy
Barthe, G., Köpf, B., Olmedo, F., & Zanella-Béguelin, S. (2012) · ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL) · doi:10.1145/2103656.2103670 · Cited by 131
Federated Model Distillation with Noise-Free Differential Privacy
Sun, L., & Lyu, L. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/216 · Cited by 114
Differential privacy under fire
Haeberlen, A., Pierce, B. C., & Narayan, A. (2011) · ScholarlyCommons (University of Pennsylvania) · Cited by 130
Local Privacy, Data Processing Inequalities, and Statistical Minimax RatesPreprint
Duchi, J. C., Jordan, M. I., & Wainwright, M. J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1302.3203 · Cited by 150
“entries distributed as Laplace(αn) provides differential privacy [23]; the associated mean-squared error is at most”
BackgroundPrivacy-Preserving Artificial Intelligence Techniques in Biomedicine
Torkzadehmahani, R., Nasirigerdeh, R., Blumenthal, D. B., Kacprowski, T., List, M., Matschinske, J., Spaeth, J., Wenke, N. K., & Baumbach, J. (2022) · Methods of Information in Medicine · doi:10.1055/s-0041-1740630 · Cited by 111
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling
Feldman, V., McMillan, A., & Talwar, K. (2022) · Annual Symposium on Foundations of Computer Science · doi:10.1109/focs52979.2021.00096 · Cited by 204
Private Release of Graph Statistics using Ladder Functions
Zhang, J., Cormode, G., Procopiuc, C. M., Srivastava, D., & Xiao, X. (2015) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/2723372.2737785 · Cited by 125
“This issue could be alleviated by combining smooth sensitivity with Laplace noise, but the resulting solution would only achieve a weakened version of ε -differential privacy (referred to as ( ε , δ ) -differential privacy [10]).”
BackgroundDifferential Privacy for Functions and Functional DataPreprint
HallRob, RinaldoAlessandro, & WassermanLarry (2010) · arXiv (Cornell University) · doi:10.1184/r1/6586565 · Cited by 126
AI-Enhanced Cloud-Edge-Terminal Collaborative Network: Survey, Applications, and Future Directions
Gu, H., Zhao, L., Han, Z., Zheng, G., & Song, S. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3338153 · Cited by 143
Deep Generative Models for Synthetic Data: A Survey
Eigenschink, P., Reutterer, T., Vamosi, S., Vamosi, R., Sun, C., & Kalcher, K. (2023) · IEEE Access · doi:10.1109/access.2023.3275134 · Cited by 102
“To account for the importance of privacy, they adapted the training of the original model to incorporate differential privacy [1], [25].”
MethodA near-optimal algorithm for differentially-private principal components
Chaudhuri, K., Sarwate, A. D., & Sinha, K. P. (2013) · doi:10.5555/2567709.2567754 · Cited by 119
Towards Security Threats of Deep Learning Systems: A Survey
He, Y., Meng, G., Chen, K., Hu, X., & He, J. (2020) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2020.3034721 · Cited by 160
“It is first proposed in [60] and proved to be effective in privacy preservation in database.”
BackgroundPrivacy in Social Networks: A Survey
Zheleva, E., & Getoor, L. C. (2011) · Springer eBooks · doi:10.1007/978-1-4419-8462-3_10 · Cited by 119
“A similar and somewhat weaker de nition of differential privacy is the one of ( , δ)-differential privacy which was developed to deal with very unlikely outputs of K [19].”
BackgroundA Comprehensive Survey on Local Differential Privacy toward Data Statistics and Analysis
Wang, T., Zhang, X., Feng, J., & Yang, X. (2020) · Sensors · doi:10.3390/s20247030 · Cited by 154
“Similar to the case that ( , δ)-DP [50] is a relaxation of -DP, ( , δ)-LDP (also called approximate LDP) is a relaxation of -LDP (also called pure LDP).”
BackgroundFedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
Xiong, Y., Wang, R., Cheng, M., Yu, F., & Hsieh, C. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01566 · Cited by 176
“There are many scenarios in which DP guarantee is necessary [2, 4, 15, 21, 45].”
BackgroundThe distributed discrete gaussian mechanism for federated learning with secure aggregation
Kairouz, P., Liu, Z., & Steinke, T. (2021) · arXiv · doi:10.48550/arxiv.2102.06387 · Cited by 117
“The closest work to ours is cpSGD (Agarwal et al., 2018), which also serves as an inspiration for much of our work. cpSGD uses a distributed version of the binomial mechanism (Dwork et al., 2006a) to achieve distributed DP.”
BackgroundMethodA Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning
Blanco-Justicia, A., Sánchez, D., Domingo‐Ferrer, J., & Muralidhar, K. (2022) · ACM Computing Surveys · doi:10.1145/3547139 · Cited by 157
“By far, the most common relaxation is (ε,δ )-DP [15], which is satisied by a randomized query function κ if, for all data sets D1 and D2 that difer in one record and all S ∈ Ranдe (κ), it holds that”
BackgroundAdvancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
Cummings, R., Desfontaines, D., Evans, D., Geambasu, R., Huang, Y., Jagielski, M., Kairouz, P., Kamath, G., Oh, S., Ohrimenko, O., et al. (2024) · Harvard Data Science Review · doi:10.1162/99608f92.d3197524 · Cited by 154
A Survey on Differentially Private Machine Learning [Review Article]
Gong, M., Xie, Y., Pan, K., Feng, K., & Qin, A. K. (2020) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2020.2976185 · Cited by 115
“In addition, it provides a possibility to violate e differential privacy by a probability d [21].”
BackgroundFLAME: Differentially Private Federated Learning in the Shuffle Model
Liu, R., Cao, Y., Chen, H., Guo, R., & Yoshikawa, M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i10.17053 · Cited by 101
Memory-aware curriculum federated learning for breast cancer classification
Jiménez-Sánchez, A., Tardy, M., González Ballester, M. A., Mateus, D., & Piella, G. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107318 · Cited by 114
“To address the second challenge, data protection, cryptographic techniques [4] or differential privacy [5], [6] are employed.”
BackgroundMethodPrivacy-Preserving Federated Learning With Malicious Clients and Honest-but-Curious Servers
Le, J., Zhang, D., Lei, X., Jiao, L., Zeng, K., & Liao, X. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3295949 · Cited by 125
“Besides, there is a property in DP that makes it particularly useful in applications, that is sequential composition [39], [40].”
BackgroundTowards an axiomatization of statistical privacy and utility
Kifer, D., & Lin, B.-R. (2010) · ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS) · doi:10.1145/1807085.1807106 · Cited by 114
Fingerprinting codes and the price of approximate differential privacy
Bun, M., Ullman, J., & Vadhan, S. (2014) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/2591796.2591877 · Cited by 193
“It is especially desirable to achieve (ε, δ)differential privacy [14, 13], which (for suitable choices of ε and δ) guarantees that no individual’s data has a significant influence on the information released about the database.”
BackgroundThe 2020 Census Disclosure Avoidance System TopDown Algorithm
Abowd, J. M., Ashmead, R., Cumings-Menon, R., Garfinkel, S., Heineck, M., Heiss, C., Johns, R., Kifer, D., Leclerc, P., Machanavajjhala, A., et al. (2022) · Harvard Data Science Review · doi:10.1162/99608f92.529e3cb9 · Cited by 200
Mechanism design in large games: incentives and privacy
Kearns, M., Pai, M., Roth, A., & Ullman, J. (2014) · Proceedings of the 5th conference on Innovations in theoretical computer science · doi:10.1145/2554797.2554834 · Cited by 112
DPPro: Differentially Private High-Dimensional Data Release via Random Projection
Xu, C., Ren, J., Zhang, Y., Qin, Z., & Ren, K. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2737966 · Cited by 112
“Definition 2 (L2-SENSITIVITY [27]): For any two neighboring databases D1 and D2, the L2-sensitivity θ(Q) of a query set Q is defined as:”
BackgroundInfluentialWang, Y., Huang, Z., Mitra, S., & Dullerud, G. E. (2017) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2017.2658190 · Cited by 111
“(3) Note that the components of the Laplace random vector are independent.”
BackgroundDifferentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso
Thakurta, A., & Smith, A. (2013) · Conference on Learning Theory · Cited by 111
A case study: privacy preserving release of spatio-temporal density in paris
Ács, G., & Castelluccia, C. (2014) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2623330.2623361 · Cited by 110
Lower Bounds in Differential Privacy
De, A. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-28914-9_18 · Cited by 98
“We now recall the Gaussian mechanism of [8] which maintains ( , δ) differential privacy.”
BackgroundInfluentialThe geometry of differential privacy: the sparse and approximate cases
Nikolov, A., Talwar, K., & Zhang, L. (2013) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/2488608.2488652 · Cited by 110
Secure multiple linear regression based on homomorphic encryption
Hall, R., Fienberg, S. E., & Nardi, Y. (2011) · Cited by 109
Mining frequent graph patterns with differential privacy
Shen, E., & Yu, T. (2013) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2487575.2487601 · Cited by 109
“An itemset pattern can be represented by an ordered list or a bitmap of item IDs Checking the existence of an itemset in a transaction only takes O(1) time, while checking whether a subgraph pattern exists in a graph is NPcomplete due to subgraph isomorphism.”
BackgroundDifferential Privacy in New Settings
Dwork, C. (2010) · Cited by 109
Self-citationNeither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
Farrand, T., Mireshghallah, F., Singh, S., & Trask, A. (2020) · PPMLP@CCS · doi:10.1145/3411501.3419419 · Cited by 149
“KEYWORDS Fairness, Bias, Differential Privacy, Data Imbalance, Deep Learning”
BackgroundInfluentialTowards Privacy for Social Networks: A Zero-Knowledge Based Definition of Privacy
Gehrke, J. E., Lui, E., & Pass, R. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19571-6_26 · Cited by 108
Publishing trajectories with differential privacy guarantees
Jiang, K., Shao, D., Bressan, S., Kister, T., & Tan, K. (2013) · International Conference on Scientific and Statistical Database Management · doi:10.1145/2484838.2484846 · Cited by 108
“[8] proposed (ε, δ)-differential privacy, which is a relaxed version of ε-differential privacy that allows privacy breaches to occur with a very small probability controlled by δ.”
BackgroundKasiviswanathan, S. P., Rudelson, M., Smith, A., & Ullman, J. (2010) · Proceedings of the forty-second ACM symposium on Theory of computing · doi:10.1145/1806689.1806795 · Cited by 105
Privacy in Deep Learning: A Survey
Mireshghallah, F., Taram, M., Vepakomma, P., Singh, A., Raskar, R., & Esmaeilzadeh, H. (2020) · arXiv · doi:10.48550/arxiv.2004.12254 · Cited by 106
“For ≥ 0, an algorithmA satisfies -DP [54, 20] if and only if for any pair of datasetsD andD′ that differ in only one element: P[A(D)= t]≤e P[A(D′)= t] ∀t (1)”
BackgroundTowards statistical queries over distributed private user data
Chen, R., Reznichenko, A., Francis, P., & Gehrke, J. E. (2012) · Cited by 106
Distributed Privacy-Preserving Aggregation of Metering Data in Smart Grids
Rottondi, C., Verticale, G., & Krauß, C. (2013) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2013.130716 · Cited by 111
“Cryptographic schemes can also be combined with differential privacy techniques in order to securely compute aggregate statistics: in [13], a protocol for the distributed generation of random noise is proposed, aimed at the distributed implementation of privacypreserving statistical databases.”
BackgroundPrivacy and Data-Based Research
Heffetz, O., & Ligett, K. (2014) · The Journal of Economic Perspectives · doi:10.1257/jep.28.2.75 · Cited by 106
A survey on federated learning: a perspective from multi-party computation
Liu, F., Zheng, Z., Shi, Y., Tong, Y., & Zhang, Y. (2023) · Frontiers of Computer Science · doi:10.1007/s11704-023-3282-7 · Cited by 118
Proving Differential Privacy via Probabilistic Couplings
Barthe, G., Gaboardi, M., Grégoire, B., Hsu, J., & Strub, P.-Y. (2016) · Proceedings of the 31st Annual ACM/IEEE Symposium on Logic in Computer Science · doi:10.1145/2933575.2934554 · Cited by 93
Is Interaction Necessary for Distributed Private Learning?
Smith, A., Thakurta, A., & Upadhyay, J. (2017) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp.2017.35 · Cited by 161
The optimal mechanism in differential privacy
Geng, Q., & Viswanath, P. (2014) · 2014 IEEE International Symposium on Information Theory · doi:10.1109/isit.2014.6875258 · Cited by 97
“[12] introduce ( , δ)-differential privacy and show that adding random noise with Gaussian distribution can preserve ( , δ)-differential privacy for real-valued query function.”
BackgroundBetween Pure and Approximate Differential Privacy
Steinke, T., & Ullman, J. (2017) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.v7i2.648 · Cited by 165
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.