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 401–500 of 1,008
Grafting Laplace and Gaussian Distributions: A New Noise Mechanism for Differential Privacy
Muthukrishnan, G., & Kalyani, S. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3306159 · Cited by 42
“The Gaussian mechanism [1], [9], [10] is the most extensively studied noise mechanism among all.”
BackgroundPrivate Data Analytics on Biomedical Sensing Data via Distributed Computation
Gong, Y., Fang, Y., & Guo, Y. (2016) · IEEE/ACM Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2016.2515610 · Cited by 42
Efficient private empirical risk minimization for high-dimensional learning
Kasiviswanathan, S. P., & Jin, H. (2016) · International Conference on Machine Learning · Cited by 70
Wang, Y., Ding, Z., Kifer, D., & Zhang, D. (2020) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3372297.3417282 · Cited by 60
“Among several popular variants of differential privacy [16, 26, 27, 43], we focus on pure differential privacy [27].”
BackgroundSecrecy by Design With Applications to Privacy and Compression
Shkel, Y. Y., Blum, R. S., & Poor, H. V. (2020) · IEEE Transactions on Information Theory · doi:10.1109/tit.2020.3041224 · Cited by 49
“The problem of partial secrecy in the setting of database privacy has been widely studied in the computer science literature; approaches such as differential privacy [2], [3], ( , δ)-differential privacy [19], and local differential privacy [20]–[22] can also be viewed through the lens of information leakage [23]–[27].”
BackgroundIndividual Privacy Accounting via a Renyi FilterPreprint
Feldman, V., & Zrnic, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.11193 · Cited by 46
“1 ([11, 10]).”
Privacy-Enhancing Technologies in Biomedical Data Science
Cho, H., Froelicher, D., Dokmai, N., Nandi, A., Sadhuka, S., Hong, M. M., & Berger, B. (2024) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-120423-120107 · Cited by 48
On the cost of differential privacy in distributed control systems
Huang, Z., Wang, Y., Mitra, S., & Dullerud, G. E. (2014) · International Conference on High Confidence Networked Systems · doi:10.1145/2566468.2566474 · Cited by 41
“Various mechanisms for achieving differential privacy have been studied in the literature [3, 12, 13].”
BackgroundLocating a Small Cluster Privately
Nissim, K., Stemmer, U., & Vadhan, S. (2016) · ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS) · doi:10.1145/2902251.2902296 · Cited by 66
“For simplicity, in the above theorem we identified X d with the real d -dimensional unit cube, quantized with grid step 1 / ( X − 1) .”
BackgroundMethodCompressive Privacy: From Information\/Estimation Theory to Machine Learning [Lecture Notes]
Kung, S. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2016.2616720 · Cited by 41
“Differential privacy In the differential privacy (DP) theory [1], a desensitizing function K is said to provide e-DP of the data if [ ( ) ] [ ( ) ] K D S e Pr K D S Pr ! # ! e l for all ( ) S K Range ! and all data sets D and Dl differing by one entry.”
Differentially Private MIMO Filtering for Event Streams
Ny, J. L., & Mohammady, M. (2017) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2017.2713643 · Cited by 49
“4) Basic Differentially Private Mechanism: The basic mechanism of Theorem 1 (see [15]), extending [30], can be used to answer queries in a differentially private way.”
On the Protection of Private Information in Machine Learning Systems: Two Recent Approches
Abadi, M., Erlingsson, U., Goodfellow, I., McMahan, H. B., Mironov, I., Papernot, N., Talwar, K., & Zhang, L. (2017) · 2017 IEEE 30th Computer Security Foundations Symposium (CSF) · doi:10.1109/csf.2017.10 · Cited by 39
“We note, however, that many of these techniques achieve a guarantee known as ( , δ)-differential-privacy [35]; while the parameter from the original definition of differential privacy can be viewed as a privacy cost [9], the additional parameter δ can be viewed as a probability of failure.”
BackgroundSelf-citationDifferentially Private Empirical Risk Minimization with Input Perturbation
Fukuchi, K., Tran, Q. K., & Sakuma, J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67786-6_6 · Cited by 52
“In recent years, differential privacy has become widely recognized as a theoretical definition for output privacy (Dwork et al., 2006b).”
Synthesizing Privacy Preserving Traces: Enhancing Plausibility With Social Networks
Zhao, P., Jiang, H., Li, J., Zeng, F., Xiao, Z. Q., Xie, K., & Zhang, G. (2019) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2019.2947452 · Cited by 45
“First, we set parameter k ∈ [5, 25], and ρ = 0.”
BackgroundMethodPrive-HD: Privacy-Preserved Hyperdimensional Computing
Khaleghi, B., Imani, M., & Rosing, T. (2020) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac18072.2020.9218493 · Cited by 51
“have also introduced a more amiable δapproximate ε-indistinguishable privacy guarantee, which allows the ε-privacy to be broken by a probability of δ [16].”
BackgroundGootjes-Dreesbach, L., Sood, M., Sahay, A., Hofmann‐Apitius, M., & Fröhlich, H. (2020) · Frontiers in Big Data · doi:10.3389/fdata.2020.00016 · Cited by 41
PIVODL: Privacy-Preserving Vertical Federated Learning Over Distributed Labels
Zhu, H., Wang, R., Jin, Y., & Liang, K. (2021) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3139055 · Cited by 46
“Differentialprivacy(DP)[33],[34]isadataprivacyprotection scheme.”
MethodDifferential Privacy in Personalized Pricing with Nonparametric Demand Models
Chen, X., Miao, S., & Wang, Y. (2022) · Operations Research · doi:10.1287/opre.2022.2347 · Cited by 52
Secure Distributed Framework for Achieving ε-Differential Privacy
Alhadidi, D., Mohammed, N., Fung, B. C. M., & Debbabi, M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31680-7_7 · Cited by 41
“Blue-collar Any_Sex [60-99) ∪Cuti = {Any_Job, Any_Sex, [1-99)} Any_Job {White-collar, Blue-collar} ∪Cuti = {White-collar,Blue-collar, Any_Sex, [1,99)}”
BackgroundInfluentialReviewing and Improving the Gaussian Mechanism for Differential PrivacyPreprint
Zhao, J., Wang, T., Bai, T., Lam, K., Xu, Z., Shi, S., Ren, X., Yang, X., Liu, Y., & Yu, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.12060 · Cited by 46
“Differential privacy [3] has received considerable interest [1], [4]–[11] since it provides a rigorous framework to quantify data privacy.”
BackgroundMethodInfluentialGuidelines for Implementing and Auditing Differentially Private SystemsPreprint
Kifer, D., Messing, S., Roth, A., Thakurta, A., & Zhang, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.04049 · Cited by 47
“Definition 1 (Dwork et al. (2006a,b)) .”
BackgroundInfluentialFed-TGAN: Federated Learning Framework for Synthesizing Tabular DataPreprint
Zhao, Z., Birke, R., Kunar, A., & Chen, L. Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.07927 · Cited by 53
“Orthogonal to FL, there is an array of privacy-preserving techniques that can be jointly applied to further strengthen privacy guarantee of GANs and FL, namely differential privacy (DP) [5, 23, 25] and homomorphic encryption (HE) [6, 10].”
BackgroundPrivate data aggregation with integrity assurance and fault tolerance for mobile crowd-sensing
Chen, J., Ma, H., & Zhao, D. Y. (2015) · Wireless Networks · doi:10.1007/s11276-015-1120-z · Cited by 40
“The first distributed solution for differentially privacy was proposed in [26].”
BackgroundVariational Bayes In Private Settings (VIPS)
Park, M., Foulds, J. R., Chaudhuri, K., & Welling, M. (2020) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11763 · Cited by 40
Convergence Rates for Differentially Private Statistical Estimation
Chaudhuri, K., & Hsu, D. (2012) · PubMed · doi:10.48550/arxiv.1206.6395 · Cited by 40
“It has been shown to have strong semantic guarantees (Dwork et al., 2006b) and is resistant to many attacks (Ganta et al., 2008) that succeed against some other definitions of privacy.”
BackgroundMethodInfluentialSecure collaborative few-shot learning
Xie, Y., Wang, H., Yu, B., & Zhang, C. B. C. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106157 · Cited by 43
Differential privacy in intelligent transportation systems
Kargl, F., Friedman, A., & Boreli, R. (2013) · Proceedings of the sixth ACM conference on Security and privacy in wireless and mobile networks · doi:10.1145/2462096.2462114 · Cited by 38
“Di↵erentially private computations can be composed, as shown in [5]: a series of n computations, where computation i is (✏i, i)-di↵erentially private, will result in the worst case in a computation that is ( P”
BackgroundLinear Queries Estimation with Local Differential PrivacyPreprint
Bassily, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.02810 · Cited by 40
Understanding Unintended Memorization in Language Models Under Federated Learning
Thakkar, O. D., Ramaswamy, S., Mathews, R., & Beaufays, F. (2021) · Proceedings of the Third Workshop on Privacy in Natural Language Processing · doi:10.18653/v1/2021.privatenlp-1.1 · Cited by 39
“To establish the notion of differential privacy (Dwork et al., 2006c,b), we first define neighboring datasets.”
BackgroundA Systematic Survey for Differential Privacy Techniques in Federated Learning
Zhang, Y., Lu, Y., & Liu, F. (2023) · Journal of Information Security · doi:10.4236/jis.2023.142008 · Cited by 49
Ganev, G., & Cristofaro, E. D. (2025) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp61157.2025.00218 · Cited by 54
“DPGAN [131] modifies the GAN training procedure to satisfy DP.”
Evading Curse of Dimensionality in Unconstrained Private GLMs via Private Gradient DescentPreprint
Song, S., Steinke, T., Thakkar, O. D., & Thakurta, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06783 · Cited by 39
“Definition 2.1 (Differential privacy [12, 11]) .”
InfluentialRobin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic DataPreprint
Ganev, G., Oprisanu, B., & Cristofaro, E. D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.11429 · Cited by 39
“Furthermore, ( , δ)-DP of the output is achieved using DP-SGD [1], which sanitizes the gradients (clips the `2 norm of the individual gradients and applies Gaussian Mechanism [13] to the sum) of the discriminator during training.”
Differentially private image classification using support vector machine and differential privacy
Senekane, M. (2019) · Machine Learning and Knowledge Extraction · doi:10.3390/make1010029 · Cited by 38
“A randomized function K gives an (e, δ)-differential privacy if for all datasets D1 and D2 differing in at most one element, and all S ⊆ Range(K) [16],”
BackgroundPrivacy-Preserving Distributed Stream Monitoring
Friedman, A., Sharfman, I., Keren, D., & Schuster, A. (2014) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2014.23128 · Cited by 38
“Early works on differential privacy in a distributed setting [21], [22] studied how differential privacy could be combined with cryptographic protocols to allow one-off computations to be carried out both securely and privately.”
BackgroundMethodDuan, Y. (2009) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/1645953.1646160 · Cited by 38
“∀ ǫ, δ ≥ 0 , an algorithm A f gives ( ǫ, δ ) -differential privacy with respect to a query function Several solutions achieve differential privacy (e.g., [10, 3, 15, 13, 2]).”
BackgroundMethodInfluentialDifferentially Private Oblivious RAM
Wagh, S., Cuff, P., & Mittal, P. (2018) · Proceedings on Privacy Enhancing Technologies · doi:10.1515/popets-2018-0032 · Cited by 47
“[20] with its ( , δ)-differential privacy modification [21].”
BackgroundAttacking and Protecting Tunneled Traffic of Smart Home Devices
Alshehri, A., Granley, J., & Yue, C. (2020) · ACM Conference on Data and Application Security and Privacy (CODASPY) · doi:10.1145/3374664.3375723 · Cited by 44
“Consider an obfuscation algorithm A which pads network packets”
MethodSoK: Differential Privacy as a Causal Property
Tschantz, M. C., Sen, S., & Datta, A. (2020) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp40000.2020.00012 · Cited by 62
“(His work is more similar to the local formulation of DP [16].)”
BackgroundGhazi, B., Golowich, N., Kumar, R., Pagh, R., & Velingker, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77883-5_16 · Cited by 60
“While many formal notions of privacy have been proposed (see, e.g., [76]), differential privacy (DP) [46,44] has emerged as the gold standard due to its broad applicability and nice features such as composition and post-processing (see, e.g., [51,93] for a comprehensive overview).”
Fully Distributed Privacy Preserving Mini-batch Gradient Descent Learning
Danner, G., & Jelasity, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19129-4_3 · Cited by 43
“In our distributed setup, this noise term can be computed in a distributed and secure way [10].”
BackgroundPrivacy in Sensor-Driven Human Data Collection: A Guide for PractitionersPreprint
Stopczynski, A., Pietri, R., Pentland, A., Lazer, D. M. J., & Lehmann, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1403.5299 · Cited by 42
“in [120], where an efficient distributed protocol for generating shares of random noise and securing against malicious participants was described.”
BackgroundDP-LDMs: Differentially Private Latent Diffusion Models
Liu, M. F., Lyu, S., Vinaroz, M., & Park, M. (2023) · Transactions on machine learning research · doi:10.48550/arxiv.2305.15759 · Cited by 46
“∆ µ is often called the global sensitivity (Dwork et al., 2006; 2014), which is the maximum difference in L 2 - norm given two neighbouring D and D ′ , || µ ( D ) − µ ( D ′ ) || 2 .”
Training Production Language Models without Memorizing User Data
Ramaswamy, S., Thakkar, O., Mathews, R., Andrew, G., McMahan, H. B., & Beaufays, F. (2020) · arXiv · doi:10.48550/arxiv.2009.10031 · Cited by 37
“Differential privacy (DP) [DMNS06], [DKM + 06a] provides a gold standard for performing learning tasks over sensitive data.”
BackgroundA federated learning scheme meets dynamic differential privacy
Guo, S., Wang, X., Long, S., Liu, H., Liu, H., & Sam, T. H. (2023) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12187 · Cited by 41
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
Fan, C., Liu, J., Hero, A. O., & Liu, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72664-4_16 · Cited by 67
Pure Differentially Private Summation from Anonymous Messages
Ghazi, B., Golowich, N., Kumar, R., Manurangsi, P., Pagh, R., & Velingker, A. (2020) · IT University Of Copenhagen (IT University of Copenhagen) · doi:10.4230/lipics.itc.2020.15 · Cited by 37
The Challenges of Privacy and Access Control as Key Perspectives for the Future Electric Smart Grid
Triantafyllou, A., Jimenez, J. A. P., del Real, A. J., Λάγκας, Θ., Rantos, K., & Sarigiannidis, P. G. (2020) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2020.3037517 · Cited by 41
“In more detail, the main idea behind differential privacy [76], [77] is that it uses random noise to bound the publicly visible information that can be acquired about a user in the dataset.”
BackgroundConnecting Robust Shuffle Privacy and Pan-Privacy
Balcer, V., Cheu, A., Joseph, M., & Mao, J. (2021) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611976465.142 · Cited by 53
Confidentiality Protection in the 2020 US Census of Population and Housing
Abowd, J. M., & Hawes, M. B. (2022) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-010422-034226 · Cited by 48
“There are now several DP frameworks: pure DP (Dwork et al. 2006b), approximate DP (Dwork et al. 2006a), concentrated DP (Dwork & Rothblum 2016), zero-concentrated DP (z-CDP) (Bun & Steinke 2016), Rényi DP (Mironov 2017), and f -DP (Dong et al. 2020), among others.”
Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading
Kong, F., Wang, X., Xiang, J., Yang, S., Wang, X., Yue, M., Zhang, J., Zhao, J., Han, X., Dong, Y., et al. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.03.028 · Cited by 47
“…contributions in the following areas: (1) We propose a novel FL framework named FACL, which ensures privacy preservation and minimizes unnecessary data transmission, aiming to achieve better diagnosis and Gleason grading of prostate cancer based on large-scale and multicenter pathology…”
InfluentialGrataloup, A., & Kurpicz-Briki, M. (2024) · Frontiers in Digital Health · doi:10.3389/fdgth.2024.1495999 · Cited by 38
A Supermodularity-Based Differential Privacy Preserving Algorithm for Data Anonymization
Fouad, M. R., Elbassioni, K., & Bertino, E. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.107 · Cited by 36
Verifiable differential privacy
Narayan, A., Feldman, A. J., Papadimitriou, A., & Haeberlen, A. (2015) · European Conference on Computer Systems · doi:10.1145/2741948.2741978 · Cited by 55
“A few recent systems have considered richer threat models: for instance, there are some solutions [14, 33, 36] that can process queries over multiple databases whose curators do not trust each other, while others [10] can prevent malicious subjects from providing data that would distort the results.”
BackgroundA Compressive Privacy approach to Generalized Information Bottleneck and Privacy Funnel problems
Kung, S. (2017) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2017.07.002 · Cited by 36
Optimal Differentially Private Algorithms for k-Means Clustering
Huang, Z., & Liu, J. (2018) · ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS) · doi:10.1145/3196959.3196977 · Cited by 56
“For example, Gaussian mechanism [6, 7] handles problems with numerical outputs by adding Gaussian noises that are inverse proportional to the privacy parameter, and are proportional the global sensitivity of the output.”
BackgroundA Blockchain-Based Approach for Saving and Tracking Differential-Privacy Cost
Zhao, Y., Zhao, J., Kang, J., Zhang, Z., Niyato, D. T., Shi, S., & Lam, K. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3058209 · Cited by 39
“Among various mechanisms to achieve DP, the Gaussian mechanism for real-valued queries proposed in [6] has received much attention.”
BackgroundInfluentialThakur, A., Sharma, P., & Clifton, D. A. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3134835 · Cited by 36
“The security protocols such as secure multi-party computation [14] or differential privacy [15] can easily be incorporated in the proposed framework.”
BackgroundLessons Learned: Surveying the Practicality of Differential Privacy in the Industry
Garrido, G. M., Liu, X., Matthes, F., & Song, D. X. (2023) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2023-0045 · Cited by 36
Differentially Private Federated Clustering Over Non-IID Data
Li, Y., Wang, S., Chi, C., & Quek, T. Q. S. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3312852 · Cited by 45
“In particular, it is widely known that DP protects privacy at the cost of learning performance loss [21], and balancing the tradeoff between protection level and convergence performance, so-called the privacy–utility tradeoff, is essential in practical FL applications.”
BackgroundCombining homomorphic encryption and differential privacy in federated learning
Sébert, A. G., Checri, M., Stan, O., Sirdey, R., & Gouy‐Pailler, C. (2023) · Conference on Privacy, Security and Trust · doi:10.1109/pst58708.2023.10320195 · Cited by 49
“Differential Privacy (DP) [12] is a gold standard concept in privacy-preserving data analysis.”
BackgroundDifferentially Private Bayesian Learning on Distributed Data
Heikkilä, M., Lagerspetz, E., Kaski, S., Shimizu, K., Tarkoma, S., & Honkela, A. (2017) · Helda - University of Helsinki Institutional Repository · doi:10.48550/arxiv.1703.01106 · Cited by 62
“Differential privacy, originally introduced by Dwork et al. (2006), is a method that gives strict, mathematically provable guarantees against intrusions on individual privacy.”
BackgroundMethodSaeidian, S., Cervia, G., Oechtering, T. J., & Skoglund, M. (2023) · IEEE Transactions on Information Theory · doi:10.1109/tit.2023.3304378 · Cited by 55
“Differential privacy resolves this problem by introducing approximate DP (i.e., ( ϵ, δ ) -DP defined based on an additive parameter δ [66]) which is closed under post-processing.”
MethodTight on Budget? Tight Bounds for r-Fold Approximate Differential Privacy
Meiser, S., & Mohammadi, E. (2018) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3243734.3243765 · Cited by 67
“To extend the applicability of DP, approximate differential privacy [4] (ADP) has been introduced, which allows for distributions to exceed a limiting factor ε , as long as this deviation can be limited to a value δ as follows: ∀S ⊆ U, Pr [M(D1) ∈ S] ≤ eε · Pr [M(D2) ∈ S] + δ .”
BackgroundStatistical Data Privacy: A Song of Privacy and Utility
Slavković, A., & Seeman, J. (2022) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-033121-112921 · Cited by 48
Differentially private federated learning with Laplacian smoothing
Liang, Z., Wang, B., Gu, Q., Osher, S., & Yao, Y. (2024) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2024.101660 · Cited by 41
“[16] Cynthia Dwork, Krishnaram Kenthapadi, Frank McSherry, Ilya Mironov, and Moni Naor.”
BackgroundOptimal error of query sets under the differentially-private matrix mechanism
Li, C., & Miklau, G. (2013) · International Conference on Database Theory · doi:10.1145/2448496.2448529 · Cited by 35
“(Gaussian mechanism [8, 22])Given an m× n query matrix W, the randomized algorithm G that outputs the following vector is ( , δ)-differentially private:”
BackgroundNot one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning
Zhao, B. Z. H., Kâafar, M. A., & Kourtellis, N. (2020) · Cloud Computing Security Workshop · doi:10.1145/3411495.3421352 · Cited by 52
“Differential privacy (DP) mathematically defines the protection offered in regards to the privacy of a single data vector, whether that is representative of an individual, or a single temporal event [10, 11].”
BackgroundMethodLocally Private Mean Estimation: Z-test and Tight Confidence IntervalsPreprint
Gaboardi, M., Rogers, R., & Sheffet, O. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.08054 · Cited by 48
“We use the following mechanisms I Gaussian Noise [2]: Suppose each datum is sampled from an interval I of length `.”
BackgroundMethodDifferentially private cross-silo federated learningPreprint
Heikkilä, M., Koskela, A., Shimizu, K., Samuel Kaski, A., & Honkela, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.05553 · Cited by 37
“The problem of distributed DP was first formulated in [16], who propose to generate DP noise collaboratively using a SMC protocol.”
MethodDistributed, Private, Sparse Histograms in the Two-Server Model
Bell, J., Gascón, A., Ghazi, B., Kumar, R., Manurangsi, P., Raykova, M., & Schoppmann, P. (2022) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3548606.3559383 · Cited by 49
“A natural idea for achieving strong privacy and high accuracy in a distributed setting is to use MPC to execute central DP mechanisms [30].”
BackgroundMethodDifferentially private false discovery rate control
Dwork, C., Su, W., & Zhang, L. (2021) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.755 · Cited by 45
Self-citationRecent advances and future challenges in federated recommender systems
Harasic, M., Keese, F.-S., Mattern, D., & Paschke, A. (2023) · International Journal of Data Science and Analytics · doi:10.1007/s41060-023-00442-4 · Cited by 41
“The assumption of a trusted central instance creates a single point of failure, and in untrusted and distributed scenarios, local or distributed DP is preferred [103, 111].”
HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
Qiu, P., Zhang, X., Ji, S., Fu, C., Yang, X., & Wang, T. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3356164 · Cited by 44
“According to the definition of Approximate DP [73], the analysis also indicates that the hashing operation satisfies (ϵ, δ) -DP, where δ = 1 − e ϵ 2 .”
MethodPrivacy-Assured Aggregation Protocol for Smart Metering: A Proactive Fault-Tolerant Approach
Won, J., Ma, C. Y. T., Yau, D. K. Y., & Rao, N. S. V. (2015) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2015.2425422 · Cited by 34
“Dwork et al. [10] show that Gaussian noise provides -DP, where is the probability that the loss of privacy is not bounded by .”
BackgroundReal-Time Data Processing Architecture for Multi-Robots Based on Differential Federated Learning
Zhou, W., Li, Y., Chen, S., & Ding, B. (2018) · 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/smartworld.2018.00106 · Cited by 33
Wang, B., Li, H., Guo, Y., & Ren, X. (2023) · Sensors · doi:10.3390/s23115219 · Cited by 33
Fan, J., Shar, L. K., Zhang, R., Liu, Z., Yang, W., Niyato, D. T., & Lam, K.-Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3653434 · Cited by 40
“To address this challenge, DP o ff ers a mathematically rigorous framework for secure data analysis and model sharing [127], [128], [129].”
Privacy-Preserving Selective Aggregation of Online User Behavior Data
Qian, J., Qiu, F., Wu, F., Ruan, N., Chen, G., & Tang, S. (2016) · IEEE Transactions on Computers · doi:10.1109/tc.2016.2595562 · Cited by 33
“The latter parameter d relaxes the strict relative shift of probability in some cases, where Inequation (1) cannot be satisfied without a non-zero d [20].”
BackgroundInfluentialDeep Domain Adaptation With Differential Privacy
Wang, Q., Li, Z., Zou, Q., Zhao, L., & Wang, S. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.2983254 · Cited by 38
“We also add a term δ introduced by [45].”
BackgroundPublishing Graphs Under Node Differential Privacy
Jian, X., Wang, Y., & Chen, L. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3128946 · Cited by 33
“Definition 1 ( ð (cid:2); d Þ -Differential Privacy [21]).”
FEVERLESS: Fast and Secure Vertical Federated Learning Based on XGBoost for Decentralized Labels
Wang, R., Ersoy, O., Zhu, H., Jin, Y., & Liang, K. (2022) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2022.3227326 · Cited by 44
“Since we apply differential privacy (Dwork et al. (2006a;b)), the summation cannot leak information regarding the inputs.”
BackgroundMethodInfluentialTriangle Counting With Local Edge Differential Privacy
Eden, T., Liu, Q. C., Raskhodnikova, S., & Smith, A. (2025) · Random Structures and Algorithms · doi:10.1002/rsa.70002 · Cited by 40
“To address this, the localmodel of differential privacy was proposed (Dwork, McSherry, et al. 2006; Evfimievski et al. 2003; Kasiviswanathan et al. 2011) and is now used in many industry deployments (Bittau et al. 2017; Cormode et al. 2018; Differential Privacy Team Apple 2017; Ding et al. 2017;…”
Ask a Better Question, Get a Better Answer A New Approach to Private Data Analysis
Dwork, C. (2006) · Lecture notes in computer science · doi:10.1007/11965893_2 · Cited by 33
“A different tack was taken in [11], where, using cryptographic techniques for secure function evaluation, the data collector/protector is replaced by a distributed privacy mechanism.”
MethodSelf-citationPrivate context-aware recommendation of points of interest: An initial investigation
Riboni, D., & Bettini, C. (2012) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2012.6197582 · Cited by 33
“A possible solution to improve the quality of service is to adopt a relaxed form of differential privacy, like the one proposed in [19].”
BackgroundMethodA Practical Framework for Privacy-Preserving Data Analytics
Fan, L., & Jin, H. (2015) · International World Wide Web Conference (WWW) · doi:10.1145/2736277.2741122 · Cited by 33
“The ( (cid:15), δ ) -indistinguishability [11, 21] relaxes the bound of (cid:15) -differential privacy by introducing an additive term δ .”
BackgroundPrivacy-Preserving Data Mining: A Survey
Aggarwal, C. C., & Yu, P. S. (2007) · Springer eBooks · doi:10.1007/978-0-387-48533-1_18 · Cited by 42
“Examples of methods which perturb the query result include [19, 33, 39, 40 , 41].”
BackgroundMethodDistributed Differentially Private Algorithms for Matrix and Tensor Factorization
Imtiaz, H., & Sarwate, A. D. (2018) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2018.2877842 · Cited by 35
A Novel Secure and Efficient Data Aggregation Scheme for IoT
Li, R., Sturtivant, C., Yu, J., & Cheng, X. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2848962 · Cited by 32
Zhang, C. B. C., Hu, X., Xie, Y., Gong, M., & Yu, B. (2020) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2019.00112 · Cited by 38
“In addition, the parameter δ , which provides a possibility to violate ε -differential privacy, does not exist in the original definition of ε -differential privacy (Dwork et al., 2006a).”
BackgroundGenerative adversarial networks enhanced location privacy in 5G networks
Qu, Y., Zhang, J., Li, R., Zhang, X., Zhai, X., & Yu, S. (2020) · Science China Information Sciences · doi:10.1007/s11432-019-2834-x · Cited by 35
“The primary advantage is to provide solid mathematical foundation to privacy preservation [6,7].”
BackgroundPublishing Trajectory with Differential Privacy: A Priori vs. A Posteriori Sampling Mechanisms
Shao, D., Jiang, K., Kister, T., Bressan, S., & Tan, K. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40285-2_31 · Cited by 32
“[5] proposed (ε, δ)-differential privacy, where δ bounds the probability that ε-differential privacy does not happen.”
BackgroundA Review of Differential Privacy in Individual Data Release
Wang, J., Liu, S., & Li, Y. (2015) · International Journal of Distributed Sensor Networks · doi:10.1155/2015/259682 · Cited by 33
“Definition 2 ((ε, δ)-differential privacy [24, 25]).”
PrOLoc: resilient localization with private observers using partial homomorphic encryption
Alanwar, A., Shoukry, Y., Chakraborty, S., Martin, P. D., Paulo Tabuada, B., & Srivastava, M. B. (2017) · ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1145/3055031.3055080 · Cited by 32
“In [32], each observer generated his share of the aggregate noise required for differential privacy [14] and sent encrypted, obfuscated data to the aggregator.”
BackgroundLocation protection method for mobile crowd sensing based on local differential privacy preference
Wang, J., Wang, Y., Zhao, G., & Zhao, Z. (2019) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-019-00774-8 · Cited by 32
Probabilistic Relational Reasoning via Metrics
de Amorim, A. A., Gaboardi, M., Hsu, J., & Katsumata, S.-Y. (2019) · ACM/IEEE Symposium on Logic in Computer Science (LICS) · doi:10.1109/lics.2019.8785715 · Cited by 36
“One example is (ε, δ)differential privacy [11], a relaxation of ε-differential privacy that allows privacy violations with a small probability δ; in return, (ε, δ)-differential privacy can allow significantly more accurate data analyses.”
BackgroundPrivacy Enhancing Technologies
Cristofaro, E. D., & Wright, M. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39077-7 · Cited by 32
Differentially Private Bayesian Optimization
Kusner, M. J., Gardner, J. R., Garnett, R., & Weinberger, K. Q. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1501.04080 · Cited by 21
Calibrating Noise to Variance in Adaptive Data AnalysisPreprint
Feldman, V., & Steinke, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.07196 · Cited by 36
The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower BoundsPreprint
Cai, T., Wang, Y., & Zhang, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.03900 · Cited by 34
“The need for data privacy protection has in turn inspired the development of formal criteria and frameworks for data privacy, with differential privacy [20, 21] (and its variants [33, 23, 41, 16]) being the most widely studied in theory [24, 22, 26, 1], and adopted in practice [14, 2, 15, 28].”
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.