Practical Secure Aggregation for Privacy-Preserving Machine Learning
The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
Abstract
We design a novel, communication-efficient, failure-robust protocol for secure aggregation of high-dimensional data. Our protocol allows a server to compute the sum of large, user-held data vectors from mobile devices in a secure manner (i.e. without learning each user's individual contribution), and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. We prove the security of our protocol in the honest-but-curious and active adversary settings, and show that security is maintained even if an arbitrarily chosen subset of users drop out at any time. We evaluate the efficiency of our protocol and show, by complexity analysis and a concrete implementation, that its runtime and communication overhead remain low even on large data sets and client pools. For 16-bit input values, our protocol offers $1.73 x communication expansion for 210 users and 220-dimensional vectors, and 1.98 x expansion for 214 users and 224-dimensional vectors over sending data in the clear.
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
“Although SMC guarantees that none of the parties shares anything with each other or with any third party, it can not prevent an adversary from learning some individual information”
From Federated Learning for Healthcare Informatics (2021) · cites this paper as [8]
In the citing paper
“By combining local inference with trusted aggregation, TDAI can enhance both privacy and robustness of anomaly detection pipelines [239].”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [239]
In the citing paper
“FL is still in its infancy and is still vulnerable to various challenges [148,149].”
From Smart Wearables for the Detection of Cardiovascular Diseases: A Systematic Literature Review (2023) · cites this paper as [148]
In the citing paper
“Therefore, many FL frameworks use secure aggregation [81], [82], [83], [84] algorithms in the aggregation process, at which point most of the poisoning attack defense methods mentioned above will be invalid.”
From Poisoning attacks in federated learning: A survey (2023) · cites this paper as [81]
In the citing paper
“Bonawitz et al. [62] introduce a secure aggregation protocol for protecting individual model updates.”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [62]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
New directions in cryptography
Diffie, W., & Hellman, M. (1976) · IEEE Transactions on Information Theory · doi:10.1109/tit.1976.1055638 · Cited by 14,713
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 1×
“maintains a private database of her text messages securely on her own mobile device, and a shared global model is trained under the coordination of a central server based upon highly processed, minimally scoped, ephemeral updates from users [20], [10].”
BackgroundSelf-citationShamir, A. (1979) · Communications of the ACM · doi:10.1145/359168.359176 · Cited by 13,756 · cited 1×
“We rely on Shamir’s t -out-of- n Secret Sharing [38], which allows a user to split a secret s into n shares, such that any t shares can be used to reconstruct s , but any set of at most t − 1 shares gives no information about s .”
Method(2016) · Cited by 11,679
Deep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578 · cited 3×
“This is particular advantageous in the local privacy setting [13], which offers provable guarantees for the protection of individual training examples [14], [15] even when the data aggregator is not assumed to be trusted [16], [17].”
BackgroundMethodSelf-citationThe Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
Dwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291 · cited 1×
“In such cases, secure aggregation composes well with differential privacy [12].”
BackgroundMembership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Federated Learning: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766
Self-citation
Research works printed but not linked: 3
- Stephen Advokat. 1987. Publication Of Bork's Video Rentals Raises Privacy Issue. Chicago Tribune (1987).
- Michael Barbaro, Tom Zeller, and Saul Hansell. 2006. A face is exposed for AOL searcher no. 4417749. New York Times 9, 2008 (2006).
- Elaine Shi, HTH Chan, Eleanor Rieffel, Richard Chow, and Dawn Song. 2011. Privacy-preserving aggregation of time-series data. In Annual Network & Distributed System Security Symposium (NDSS). Internet Society.
Cited by
Items 501–600 of 1,035
SmartPC: Hierarchical Pace Control in Real-Time Federated Learning System
Li, L., Xiong, H., Guo, Z., Wang, J., & Xu, C. (2019) · IEEE Real-Time Systems Symposium (RTSS) · doi:10.1109/rtss46320.2019.00043 · Cited by 88
SAQE: practical privacy-preserving approximate query processing for data federations
Bater, J., Park, Y., He, X. Q., Wang, X. S., & Rogers, J. (2020) · Proceedings of the VLDB Endowment · doi:10.14778/3407790.3407854 · Cited by 88
PPCL: Privacy-preserving collaborative learning for mitigating indirect information leakage
Yan, H., Hu, L. F., Xiang, X., Liu, Z., & Yuan, X. (2020) · Information Sciences · doi:10.1016/j.ins.2020.09.064 · Cited by 87
The Different Faces of AI Ethics Across the World: A Principle-to-Practice Gap Analysis
Tidjon, L. N., & Khomh, F. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3225132 · Cited by 89
“Some research has been done to define various metrics for fairness [125], [133], discrimination and bias [133], privacy [126], [134], [135], [136], [137], [138], security [126], [136], [139], [140], robustness [127], [141], [142], [143], [144], [145], [146], explain-ability [147], [148], [149],…”
BackgroundMethodSai, S., Chamola, V., Choo, K. R., Sikdar, B., & Rodrigues, J. J. P. C. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3232793 · Cited by 89
“Federated learning (FL) [59], [60] is a technique that trains an ML algorithm in multiple decentralized devices on their local data without exchanging the data.”
MethodSafeFL: MPC-friendly Framework for Private and Robust Federated Learning
Gehlhar, T., Marx, F., Schneider, T. H., Suresh, A., Wehrle, T., & Yalame, H. (2023) · IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw59333.2023.00012 · Cited by 88
“To address this issue, secure aggregation (SA) techniques have been proposed, in which users send encrypted local updates to the aggregator, who can only access the combined update rather than individual ones [8], [15], [36], [59].”
Distributed additive encryption and quantization for privacy preserving federated deep learning
Zhu, H., Wang, R., Jin, Y., Liang, K., & Ning, J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.062 · Cited by 89
FedLess: Secure and Scalable Federated Learning Using Serverless Computing
Grafberger, A., Chadha, M., Jindal, A., Gu, J., & Gerndt, M. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9672067 · Cited by 87
“Investigating the use of other secure aggregation methods such as Additive Masking [57] which require complex interaction between clients, is of our interest in the future.”
BackgroundInfluentialOgundokun, R. O., Misra, S., Maskeliūnas, R., & Damaševičius, R. (2022) · Information · doi:10.3390/info13050263 · Cited by 87
“To maintain privacy, Google’s planned federated learning [8] uses a combination of secure convergence and differential confidentiality.”
BackgroundLi, S., & Avestimehr, S. (2020) · Foundations and Trends® in Communications and Information Theory · doi:10.1561/0100000103 · Cited by 88
SecFed: A Secure and Efficient Federated Learning Based on Multi-Key Homomorphic Encryption
Cai, Y., Ding, W., Xiao, Y., Yan, Z., Liu, X., & Wan, Z. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3336977 · Cited by 89
“Bonawitz et al. [14] first constructed the SMC protocol to achieve secure aggregation, and the authors constructed a privacy computation process using double-masking.”
BackgroundMethodFederated learning meets blockchain at 6G edge: a drone-assisted networking for disaster response
Pokhrel, S. R. (2020) · Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond · doi:10.1145/3414045.3415949 · Cited by 65
An Approach for Peer-to-Peer Federated Learning
Wink, T., & Nochta, Z. (2021) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w52860.2021.00034 · Cited by 85
TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning
Xu, R., Li, B. H., Li, C., Joshi, J. B. D., Ma, S., & Li, J. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3350206 · Cited by 86
“The increasing demand for privacy-preserving FL (PPFL) solutions has resulted in a variety of methods being offered in recent research [10], [11], [12], [13], [14], [15], [16], [17], [18].”
BackgroundMethodInfluentialFederatedScope: A Flexible Federated Learning Platform for Heterogeneity
Xie, Y., Wang, Z., Gao, D., Chen, D., Yao, L., Kuang, W., Li, Y., Ding, B., & Zhou, J. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3579075.3579081 · Cited by 84
“To further satisfy different levels of protection requirements, various privacy protection techniques can be integrated into federated learning, such as Differential Privacy (DP) [61, 65], Homomorphic Encryption (HE) [19, 26], and Secure Multi-Party Computation (MPC) [6, 49].”
BackgroundMethodEfficient, Private and Robust Federated Learning
Hao, M., Li, H., Xu, G., Chen, H., & Zhang, T. (2021) · Annual Computer Security Applications Conference · doi:10.1145/3485832.3488014 · Cited by 84
“To mitigate the information leakage issue, a variety of secure aggregation schemes based on cryptographic protocols [2] [50] [7] [10] have been proposed and employed in improving the original FL systems.”
MethodFederated Learning as a Privacy Solution - An Overview
Khan, M., Glavin, F. G., & Nickles, M. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2022.12.227 · Cited by 84
What are the trend and core knowledge of information security? A citation and co-citation analysis
Shiau, W., Wang, X., & Zheng, F. (2023) · Information & Management · doi:10.1016/j.im.2023.103774 · Cited by 85
Olszewski, D., Lu, A., Stillman, C., Warren, K., Kitroser, C., Pascual, A., Ukirde, D., Butler, K. R. B., & Traynor, P. (2023) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3576915.3623130 · Cited by 85
FedMut: Generalized Federated Learning via Stochastic Mutation
Hu, M., Cao, Y., Li, A., Li, Z., Liu, C., Li, T., Chen, M., & Liu, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i11.29146 · Cited by 84
State of the Art in Parallel and Distributed Systems: Emerging Trends and Challenges
Dai, F., Hossain, M. A., & Wang, Y. (2025) · Electronics · doi:10.3390/electronics14040677 · Cited by 86
A Survey on Collaborative Deep Learning and Privacy-Preserving
Zhang, D., Chen, X., Wang, D., & Shi, J. (2018) · 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC) · doi:10.1109/dsc.2018.00104 · Cited by 63
“Reference [23] puts forward a secure aggregation protocol based on [30].”
BackgroundMethodNaseri, M., Hayes, J., & Cristofaro, E. D. (2020) · arXiv (Cornell University) · Cited by 84
Orchestra: Unsupervised Federated Learning via Globally Consistent ClusteringPreprint
Lubana, E. S., Tang, C. I., Kawsar, F., Dick, R. P., & Mathur, A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.11506 · Cited by 85
Privacy-preserving Byzantine-robust federated learning
Ma, X., Zhou, Y., Wang, L., & Miao, M. (2021) · Computer Standards & Interfaces · doi:10.1016/j.csi.2021.103561 · Cited by 83
Edge Learning: The Enabling Technology for Distributed Big Data Analytics in the Edge
Zhang, J., Qu, Z., Chen, C., Wang, H., Zhan, Y., Ye, B., & Guo, S. (2021) · ACM Computing Surveys · doi:10.1145/3464419 · Cited by 83
“Bonawitz et al. use MPC to privately compute sums of model parameter updates from individual participants without revealing sensitive information to any party including an aggregator which is referred to as Secure Aggregation [8].”
Security and privacy-aware Artificial Intrusion Detection System using Federated Machine Learning
Kumar, K. P. S., Nair, S., Roy, D. G., Rajalingam, B., & Kumar, R. S. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107440 · Cited by 83
Privacy-Preserving and Low-Latency Federated Learning in Edge Computing
He, C., Liu, G., Guo, S., & Yang, Y. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3171767 · Cited by 83
“According to work [29], [35], the additive HE-based FL (AHE-based FL) algorithm has the same accuracy as the FedAVG algorithm [15].”
MethodClustered Federated Learning in Heterogeneous Environment
Yan, Y., Tong, X., & Wang, S. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3264740 · Cited by 85
Blockchain analytics and artificial intelligence
Dillenberger, D. N., Novotny, P., Zhang, Q., Jayachandran, P., Gupta, H., Hans, S., Verma, D., Chakraborty, S., Thomas, J. J., Walli, M. M., et al. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2900638 · Cited by 82
Differentially Private Meta-Learning
Li, J., Khodak, M., Caldas, S., & Talwalkar, A. (2019) · arXiv · doi:10.48550/arxiv.1909.05830 · Cited by 82
“MPC is a cryptographic technique that allows parties to calculate a function of their inputs while also maintaining the privacy of each individual party’s inputs (Bonawitz et al., 2017).”
BackgroundElastic Aggregation for Federated Optimization
Chen, D., Hu, J., Tan, V. J., Wei, X., & Wu, E. (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/cvpr52729.2023.01173 · Cited by 84
“Nevertheless, federated learning raises several issues and has been the topic of much research effort, focusing on the issues of generalization and fairness [33, 42], the design of more efficient communication strategies [4,24,26,27,51,52], the study of lower bounds [55], differential privacy guarantees [2], security…”
BackgroundFederated Adversarial Debiasing for Fair and Transferable Representations
Hong, J., Zhu, Z., Yu, S., Wang, Z., Dodge, H. H., & Zhou, J. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467281 · Cited by 54
“The challenges from privacy concerns of sensitive personal data, limited computational resources, performance issues of localized learning all together lead to the federated learning (FL) paradigm [4, 34].”
BackgroundHashemi, H., Wang, Y., & Annavaram, M. (2021) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3466752.3480112 · Cited by 81
“The aggregate weight update over a virtual batch is essentially a customized version of secure aggregation for weigh updates [7].”
BackgroundSeizing Critical Learning Periods in Federated Learning
Yan, G., Wang, H., & Li, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20859 · Cited by 82
“Additionally, a lot of efforts have been put on exploring the privacy and fairness of federated learning (Bonawitz et al. 2017; Geyer, Klein, and Nabi 2017; Hitaj, Ateniese, and Perez-Cruz 2017; Melis et al. 2019; Zhu, Liu, and Han 2019; Mohri, Sivek, and Suresh 2019; Wang et al. 2020b).”
BackgroundEnhancing privacy preservation and trustworthiness for decentralized federated learning
Wang, L., Zhao, X., Lu, Z., Wang, L., & Zhang, S. (2023) · Information Sciences · doi:10.1016/j.ins.2023.01.130 · Cited by 81
Triastcyn, A., & Faltings, B. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.2993966 · Cited by 62
An Overview of Federated Deep Learning Privacy Attacks and Defensive Strategies
Enthoven, D., & Al-Ars, Z. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-70604-3_8 · Cited by 80
Substra: a framework for privacy-preserving, traceable and collaborative Machine LearningPreprint
Galtier, M. N., & Marini, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11567 · Cited by 82
“A classical approach to mitigate this risk is to use a mechanism of secure aggretion where the model updates are individually obfuscated by the aggregator can still output an accurate average [13].”
BackgroundAgora: A Privacy-Aware Data Marketplace
Koutsos, V., Papadopoulos, D., Chatzopoulos, D., Tarkoma, S., & Hui, P. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/icdcs47774.2020.00156 · Cited by 80
“State-of-the-art general-functionality FE schemes [41], [42] are far from practical while the system of [68] supports dropouts but has higher overhead compared to [26].”
BackgroundTowards Mitigating Device Heterogeneity in Federated Learning via Adaptive Model Quantization
Abdelmoniem, A. M., & Canini, M. (2021) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3437984.3458839 · Cited by 80
“The aggregation algorithm can be either a simple Federated averaging [29] or a variant which exploits secure aggregation [8].”
BackgroundMethodSecure Aggregation is Insecure: Category Inference Attack on Federated Learning
Gao, J., Hou, B., Guo, X., Liu, Z., Zhang, Y., Chen, K., & Li, J. (2021) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3128679 · Cited by 80
“To bypass secure aggregation [16], the attacker can exploit this ability to design the differential selection strategy , inferring the target update with the help of one spy.”
BackgroundMethodInfluentialSplitting chemical structure data sets for federated privacy-preserving machine learning
Simm, J., Humbeck, L., Zalewski, A., Sturm, N., Heyndrickx, W., Moreau, Y., Beck, B., & Schuffenhauer, A. (2021) · Journal of Cheminformatics · doi:10.1186/s13321-021-00576-2 · Cited by 83
“After each partner has updated his trunk by training on a mini-batch of own data, the trunk weight updates are aggregated through a secure protocol similar to [13] making it impossible to backtrack contributions to individual partners.”
MethodFederated Learning-Based Anomaly Detection with Isolation Forest in the IoT-Edge Continuum
Xiang, H., Zhang, X., Xu, X., Beheshti, A., Qi, L., Hong, Y., & Dou, W. (2026) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3702995 · Cited by 81
“In this part, we first review the traditional federated learning framework under IoT-edge and cloud scenarios [3].”
A blockchain-orchestrated Federated Learning architecture for healthcare consortia
Passerat‐Palmbach, J., Farnan, T., Miller, R. C., Gross, M. S., Flannery, H. L., & Gleim, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12603 · Cited by 47
“…applications have been shown to successfully leverage federated learning with a lower number of workers (20-30) Roy et al. [2019], Sheller et al. [2019] compared to Bonawitz et al. [2019], this could break the security properties of the Secure Aggregation scheme presented in Bonawitz et al. [2017].”
BackgroundSecure Byzantine-Robust Machine LearningPreprint
He, L., Karimireddy, S. P., & Jaggi, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04747 · Cited by 81
“To solve this problem, secure aggregation rules as proposed in [7] achieve guaranteed input privacy .”
BackgroundMethodInfluentialLiu, J. C., Goetz, J., Sen, S., & Tewari, A. (2021) · JMIR mHealth and uHealth · doi:10.2196/23728 · Cited by 60
“It requires significant technical expertise and engineering effort to implement federated learning under such a strong privacy requirement [43], which may be beyond the resources available in a clinical trial.”
Jiang, M., Jung, T., Karl, R., & Zhao, T. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3501808 · Cited by 79
“developed practical secure aggregation for federated learning on user-held data [5, 6] and for privacy-preserving machine learning [7], but extra key sharing is needed for each round of aggregation among all the clients, and high communication overhead is incurred.”
BackgroundMethodFLAME: Federated Learning across Multi-device Environments
Cho, H., Mathur, A., & Kawsar, F. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550289 · Cited by 79
“Recent works on this topic have investigated the issues of statistical and systems heterogeneity [24, 25, 31, 40, 76]; achieving scalability, privacy, and fairness with respect to participating clients [5, 10, 38, 41, 62]; and improving communication e ciency [1, 33, 35, 55].”
BackgroundVOSA: Verifiable and Oblivious Secure Aggregation for Privacy-Preserving Federated Learning
Wang, Y., Zhang, A., Wu, S., & Yu, S. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3226508 · Cited by 79
“There are two advantages for this setting: 1) Users significantly reduce communication complexity and overheads by only transmitting partial key information to collector without exchanging key information with all others users which is necessary in existing popular secure aggregation scheme [14], [15], [28].”
BackgroundMethodInfluentialBerkani, M. R. A., Chouchane, A., Himeur, Y., Ouamane, A., Miniaoui, S., Atalla, S., Mansoor, W., & Al-Ahmad, H. (2025) · Computers · doi:10.3390/computers14040124 · Cited by 80
“…such as robust aggregation protocols, Byzantine-resilient algorithms, anomaly detection, and privacy-preserving techniques like differential privacy and homomorphic encryption are often employed to ensure that FL systems maintain both robust model performance and data confidentiality [83,84].”
PrivacyFL: A Simulator for Privacy-Preserving and Secure Federated Learning
Mugunthan, V., Peraire-Bueno, A., & Kagal, L. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3412771 · Cited by 80
“MPC and differential privacy are the most common techniques to guarantee security and privacy in a federated environment setup [2][13][4].”
BackgroundFacing small and biased data dilemma in drug discovery with enhanced federated learning approaches
Xiong, Z., Cheng, Z., Lin, X., Xu, C., Liu, X., Wang, D., Luo, X., Zhang, Y., Jiang, H., Qiao, N., et al. (2022) · Science China Life Sciences · doi:10.1007/s11427-021-1946-0 · Cited by 69
“Both the Federated Averaging and Secure Aggregation protocol are proposed by Google’s team in separate works (McMahan et al., 2017; Bonawitz et al., 2017).”
MethodImproved Gradient Inversion Attacks and Defenses in Federated Learning
Geng, J., Mou, Y., Li, Q., Li, F., Beyan, O., Decker, S., & Rong, C. (2023) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2023.3239116 · Cited by 80
Survey: Leakage and Privacy at Inference Time
Jegorova, M., Kaul, C., Mayor, C., O'Neil, A. Q., Weir, A., Murray-Smith, R., & Tsaftaris, S. A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3229593 · Cited by 77
“, recommendation systems, mobile applications, transaction fraud detection, and healthcare [203, 206, 214, 216].”
BackgroundMistify: Automating {DNN} Model Porting for On-Device Inference at the Edge
Guo, P., Hu, B., & Hu, W. (2021) · Networked Systems Design and Implementation · Cited by 77
Yang, F., Qiao, Y., Abedin, M. Z., & Huang, C. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3151917 · Cited by 78
Blockchain and homomorphic encryption based privacy-preserving model aggregation for medical images
Kumar, R., Kumar, J., Khan, A. A., Zakria, Z., Ali, H., Bernard, C. M., Khan, R. U., & Zeng, S. (2022) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2022.102139 · Cited by 78
SoK: Cryptographic Neural-Network Computation
Ng, L. K. L., & Chow, S. S. M. (2023) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp46215.2023.10179483 · Cited by 78
“4Some may use crypto techniques [25], [26] but mostly for aggregation [27].”
MethodPrivate Aggregation from Fewer Anonymous Messages
Ghazi, B., Manurangsi, P., Pagh, R., & Velingker, A. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-45724-2_27 · Cited by 44
“[6].”
TextHide: Tackling Data Privacy in Language Understanding Tasks
Huang, Y., Song, Z., Chen, D., Li, K., & Arora, S. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.123 · Cited by 78
Free-riders in Federated Learning: Attacks and Defenses
Lin, J., Du, M., & Liu, J. (2019) · arXiv · doi:10.48550/arxiv.1911.12560 · Cited by 76
“To address the privacy concerns [28], [29], client-level differential privacy [18] is proposed to prevent leaking local clients’ private data from global model parameters, and a secure aggregation mechanism is proposed for federated learning in [27].”
BackgroundRealizing private and practical pharmacological collaboration
Hie, B., Cho, H., & Berger, B. (2018) · Science · doi:10.1126/science.aat4807 · Cited by 76
Top-k sparsification with secure aggregation for privacy-preserving federated learning
Lu, S., Li, R., Liu, W., Guan, C., & Yang, X. (2022) · Computers & Security · doi:10.1016/j.cose.2022.102993 · Cited by 76
Artificial intelligence in cancer: applications, challenges, and future perspectives
Cheng, H., & Shi, S.-S. (2025) · Molecular Cancer · doi:10.1186/s12943-025-02450-3 · Cited by 78
FLGUARD: Secure and Private Federated Learning
Nguyen, T. D., Rieger, P., Yalame, H., Möllering, H., Fereidooni, H., Marchal, S., Miettinen, M., Mirhoseini, A., Sadeghi, A., Schneider, T. H., et al. (2021) · TUbilio (Technical University of Darmstadt) · Cited by 80
Safeguarding cross-silo federated learning with local differential privacy
Wang, C., Wu, X., Liu, G., Deng, T., Peng, K., & Wan, S. (2021) · Digital Communications and Networks · doi:10.1016/j.dcan.2021.11.006 · Cited by 75
Stripelis, D., Thompson, P. M., & Ambite, J. L. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3524885 · Cited by 88
“Our proposed semi-synchronous training protocol can be run under standard privacy techniques such as differential privacy [2, 47], securemulti-party computation (MPC) [8, 30, 49], and homomorphic encryption [50, 58, 67, 76].”
MethodPrivacy-Enhanced and Verification-Traceable Aggregation for Federated Learning
Ren, Y., Li, Y., Feng, G., & Zhang, X. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3194930 · Cited by 75
“Then Bonawitz et al. [6] proposed a multiparty secure computation protocol, where the communication overheads of participants are low, and only one server is required.”
BackgroundMethodInfluentialSecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Service
Wang, S., Zheng, Y., & Jia, X. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3241615 · Cited by 75
“[40] focus on decentralized federated GNN, which allows multiple clients to train a GNN model without a centralized server and introduces the Diffie-Hellman key exchange method [41] to achieve secure model aggregation between clients.”
MethodEfficient and Secure Federated Learning for Financial Applications
Liu, T., Wang, Z., He, H., Shi, W., Lin, L., An, R., & Li, C. (2023) · Applied Sciences · doi:10.3390/app13105877 · Cited by 76
A Survey of Federated Learning for Connected and Automated Vehicles
Chellapandi, V. P., Yuan, L., Żak, S. H., & Wang, Z. (2023) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc57777.2023.10421974 · Cited by 75
“The cloud server performs a secure aggregation [8] of the received gradients/weights and updates the global model parameters that are transmitted back to the clients/edge devices.”
Hao, J., Chen, P., Chen, J., & Li, X. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.05.006 · Cited by 76
Vertical federated learning: a structured literature review
Khan, A., ten Thij, M., & Wilbik, A. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02356-y · Cited by 76
“Google initiated project in 2016 in order to establish federated learning among Android mobile users [81].”
Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy
Mireshghallah, F., Taram, M., Jalali, A., Elthakeb, A. T., Tullsen, D. M., & Esmaeilzadeh, H. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449965 · Cited by 83
“These methods have been coupled with differential privacy [5, 10, 67] or information-theoretic notions [84] to provide meaningful privacy guarantees.”
MethodJahani-Nezhad, T., Maddah-Ali, M. A., Li, S., & Caire, G. (2022) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit50566.2022.9834750 · Cited by 76
Jalali, N. A., & Chen, H. (2023) · Tsinghua Science & Technology · doi:10.26599/tst.2023.9010007 · Cited by 76
FEDERATED LEARNING ARCHITECTURES FOR PREDICTIVE QUALITY CONTROL IN DISTRIBUTED MANUFACTURING SYSTEMS
Khan, M. M., & Shehun, M. T. F. (2021) · American Journal of Interdisciplinary Studies · doi:10.63125/222nwg58 · Cited by 74
Enforcing fairness in private federated learning via the modified method of differential multipliersPreprint
Rodríguez-Gálvez, B., Granqvist, F., van Dalen, R. C., & Seigel, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.08604 · Cited by 76
“…et al., 2017] guarantees the users’ privacy by (i) making sure the aggregation of the users’ sent vectors is done securely with secure aggregation [Bonawitz et al., 2017], and (ii) clipping each users’ vectors with a clipping boundC and employing the Gaussian mechanism to the sum of the clipped…”
MethodInfluentialHuang, G., Luo, C., Wu, K., Ma, Y., Zhang, Y., & Liu, X. (2019) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2019.00166 · Cited by 75
“continuous data processing [22].”
The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
Hu, S., Li, Y., Liu, X., Li, Q., Wu, Z., & He, B. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3510540 · Cited by 72
“So instead, we applied a simple scheme: SMC via trivial secret sharing, which is also used in some FL works regarding secure aggregation [8, 9].”
MethodManaging privacy in the digital economy
Wang, C., Zhang, N., & Wang, C. (2021) · Fundamental Research · doi:10.1016/j.fmre.2021.08.009 · Cited by 74
“In horizontal FL, the distributed datasets share the same feature space, and thus, machine learning models can be computed locally and send the masked results to a centralized server, where model aggregation is performed and the results are sent back for local update [ 60 , 61 ].”
A Comprehensive Survey on Privacy-Preserving Techniques in Federated Recommendation Systems
Asad, M., Shaukat, S., Javanmardi, E., Nakazato, J., & Tsukada, M. (2023) · Applied Sciences · doi:10.3390/app13106201 · Cited by 74
“The benefits of using SMPC in FRSs include the ability to protect user data privacy, the ability to generate personalized recommendations from multiple parties collaboratively, and the ability to create a decentralized recommendation system [90,91].”
BackgroundEffects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
Truex, S., Liu, L., Gürsoy, M. E., Wei, W., & Yu, L. (2019) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa48467.2019.00019 · Cited by 75
Coordinated Backdoor Attacks against Federated Learning with Model-Dependent Triggers
Gong, X., Chen, Y., Huang, H., Liao, Y., Wang, S., & Wang, Q. (2022) · IEEE Network · doi:10.1109/mnet.011.2000783 · Cited by 72
FedeRank: User Controlled Feedback with Federated Recommender Systems
Anelli, V. W., Deldjoo, Y., Noia, T. D., Ferrara, A., & Narducci, F. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72113-8_3 · Cited by 72
Poongodi, M., Walia, R., Iwendi, C., Ahanger, T. A., Suganthi, S. T., Kamruzzaman, M. M., Bourouis, S., Alhakami, W., & Hamdi, M. (2022) · Expert Systems · doi:10.1111/exsy.13072 · Cited by 72
RetractedBFL-SA: Blockchain-based federated learning via enhanced secure aggregation
Liu, Y., Jia, Z., Jiang, Z., Lin, X., Liu, J., Wu, Q., & Susilo, W. (2024) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2024.103163 · Cited by 73
Privacy-Preserving Weighted Federated Learning Within the Secret Sharing Framework
Zhu, H., Goh, R. S. M., & Ng, W. K. (2020) · IEEE Access · doi:10.1109/access.2020.3034602 · Cited by 71
“…in the horizontal FL, the feature spaces of datasets among different organizations (data owners) are same but not overlapped over the sample spaces [5]; in the vertical FL, the sample spaces of datasets among different organizations are same but not overlapped The associate editor coordinating the…”
BackgroundCurse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning
Zawad, S., Ali, A. Z. E., Chen, P., Anwar, A., Zhou, Y., Baracaldo, N., Tian, Y., & Yan, F. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17291 · Cited by 71
Privacy-Preserving Decentralized Aggregation for Federated Learning
Jeon, B., Ferdous, S. M., Rahman, M. R., & Walid, A. (2021) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps51825.2021.9484437 · Cited by 72
Practical Privacy-Preserving Federated Learning in Vehicular Fog Computing
Li, Y., Li, H., Xu, G., Xiang, T., & Lu, R. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3150806 · Cited by 73
“Besides, we make a comparison with an MPC-based scheme PPFL [32], which also utilizes Shamir’ secret sharing as one of the technologies for constructing their framework.”
BackgroundMethodInfluentialADFL: Defending backdoor attacks in federated learning via adversarial distillation
Zhu, C., Zhang, J., Sun, X., Chen, B., & Meng, W. (2023) · Computers & Security · doi:10.1016/j.cose.2023.103366 · Cited by 71
Mao, W., Lu, X., Jiang, Y., & Zheng, H. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3350050 · Cited by 73
“Forthe dataheterogeneity,theclientsoftenhavedifferentsizesofdata samples,andthedataisevencollectedinanonindependentand identicallydistributed(Non-IID)way[17],[18].”
Secure federated learning for Alzheimer's disease detection
Mitrovska, A., Safari, P., Ritter, K., Shariati, B., & Fischer, J. (2024) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2024.1324032 · Cited by 73
Research on Financial Fraud Algorithm Based on Federal Learning and Big Data Technology
Sha, X. (2024) · IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE) · doi:10.1109/icsece61636.2024.10729568 · Cited by 71
“Shokri and Shmatikov[6] further proposed a collaborative deep learning method, which enables each collaborator to exchange only a subset of model parameter updates on the basis of independently training the local model, further reducing the risk of data exposure.”
BackgroundRFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
Mai, P., Yan, R., & Pang, Y. (2024) · neural information processing systems · doi:10.52202/079017-3314 · Cited by 72
Honeycrisp: large-scale differentially private aggregation without a trusted core
Roth, E., Noble, D., Hemenway, B., & Haeberlen, A. (2019) · ACM SIGOPS Symposium on Operating Systems Principles (SOSP) · doi:10.1145/3341301.3359660 · Cited by 71
“[15] considers a scenario that is similar to ours, and presents a protocol that also offers strong protection against user drop-out during protocol runs.”
BackgroundSynthesizing tabular data using conditional GAN
Xu, L. A. C. S. I. O. T. (2020) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 71
Cao, H., Liu, S., Zhao, R., & Xiong, X. (2020) · International Journal of Distributed Sensor Networks · doi:10.1177/1550147720919698 · Cited by 70
“The concept of federated learning 29,36 is proposed by Google recently to reduce the risk of the cloud service provider learning the personal model update.”
Background
Metadata
- Authors
- Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K.
- Affiliations
- Google (United States) (US)
- Cornell Tech (US)
- Venue
- Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2017-10-30
- Volume
- 2017
- Pages
- 1175-1191
- ISSN
- 1543-7221 (ISSN-L)
- OpenAlex
- W2767079719
- Cited by
- 3,956
- References
- 55
- Citations by year
- 2026: 701 · 2025: 712 · 2024: 643 · 2023: 564 · 2022: 400 · 2021: 436 · 2020: 299 · 2019: 152 · 2018: 42 · 2017: 7
- FWCI
- 62.37
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGSAC Conference on Computer and Communications Security (CCS) (publishedVersion)
- IACR Cryptology ePrint Archive (submittedVersion)
- 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
- secure aggregation, privacy-preserving machine learning, federated learning, high-dimensional data, communication efficiency, user dropout, honest-but-curious adversary, active adversaries, secure multi-party computation
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.