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
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
“[73], effectively handling dropping out participants at the cost of complexity of the protocol.”
BackgroundInfluentialSelf-citationFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
“SMC provides formal privacy proof for these protocols [25].”
BackgroundInfluentialFederated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210
“quires that the updates are also private to the server. Current works that aim to improve the privacy of federated learning typically build upon previous classical cryptographic protocols such as SMC [10, 42] and differential privacy [3, 8, 41, 76]. Bonawitz et al. [10] introduce an SMC protocol to protect individual…”
BackgroundFederated 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-citationFederated Learning in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565
“Although both the encryption techniques presented in [161] and [79] can prevent the curious server from extracting information, they require multi-round communications and cannot preclude collusions between the server and participants.”
BackgroundTowards Federated Learning at Scale: System Design
Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konečný, J., Mazzocchi, S., McMahan, H. B., et al. (2019) · arXiv · doi:10.48550/arxiv.1902.01046 · Cited by 2,334
“Further, several approaches to enhancing privacy guarantees for FL, including differential privacy (McMa-han et al., 2018) and Secure Aggregation (Bonawitz et al., 2017), essentially require some notion of synchronization on a fixed set of devices, so that the server side of the learning algorithm…”
BackgroundSelf-citationOpportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
“Federated learning [120] and secure aggregations [121,122] are complementary approaches that reinforce differential privacy.”
BackgroundFederated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077
“[9] developed an efficient secure aggregation protocol for federated learning, allowing a server to perform computation of high-dimensional data from mobile devices.”
MethodA survey on federated learning
Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W., & Gao, Y. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.106775 · Cited by 1,899
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2019) · ICC 2019 - 2019 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2019.8761315 · Cited by 1,875
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Nishio, T., & Yonetani, R. (2018) · arXiv · doi:10.48550/arxiv.1804.08333 · Cited by 1,875
Deep Learning in Mobile and Wireless Networking: A Survey
Zhang, C., Patras, P., & Haddadi, H. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2904897 · Cited by 1,768
Exploiting Unintended Feature Leakage in Collaborative Learning
Melis, L., Song, C., De Cristofaro, E., & Shmatikov, V. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00029 · Cited by 1,734
“[5] use secure multi-party aggregation techniques, tailored for federated learning, to let participants encrypt their updates so that the central parameter server only recovers the sum of the updates.”
MethodSCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S. J., Stich, S. U., & Suresh, A. T. (2019) · arXiv · doi:10.48550/arxiv.1910.06378 · Cited by 1,734
“…from differential privacy guarantees (Agarwal et al., 2018), stochastic optimization solutions for the agnostic formulation (Mohri et al., 2019), and incorporating cryptographic techniques (Bonawitz et al., 2017), see (Li et al., 2019a) for an in-depth survey of recent work in federated learning.”
BackgroundRobust and Communication-Efficient Federated Learning From Non-i.i.d. Data
Sattler, F., Wiedemann, S., Muller, K.-R., & Samek, W. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2944481 · Cited by 1,725
“Although it has been shown that in adversarial settings information about the training data can still be inferred from these updates [11], additional mechanisms, such as homomorphic encryption of the updates [12], [13] or differentially private training [14], can be applied to fully conceal any information about the l…”
BackgroundPrivacy-Preserving Deep Learning via Additively Homomorphic Encryption
Phong, L. T., Aono, Y., Hayashi, T., Wang, L., & Moriai, S. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2787987 · Cited by 1,662
“Due to the tool used (secret sharing in [14] vs.”
BackgroundMethodInfluentialOn the Convergence of FedAvg on Non-IID Data
Li, X., Huang, K., Yang, W., Wang, S., & Zhang, Z. (2019) · arXiv · doi:10.48550/arxiv.1907.02189 · Cited by 1,575
“The research work on FL is focused on the communication-efficiency [10, 16, 21, 27] and data privacy [1, 2, 4, 5, 17].”
BackgroundA review of applications in federated learning
Li, L., Fan, Y., Tse, M., & Lin, K.-Y. (2020) · Computers & Industrial Engineering · doi:10.1016/j.cie.2020.106854 · Cited by 1,559
“Specially, TFF integrates FedAvg for model update and Secure Aggregation for privacy concern (Bonawitz et al., 2017).”
BackgroundFederated Learning for Healthcare Informatics
Xu, J., Glicksberg, B. S., Su, C., Walker, P., Bian, J., & Wang, F. (2021) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-020-00082-4 · Cited by 1,542
“Secure multi-party computation (SMC) has a natural application to federated learning scenarios, where each individual client uses a combination of cryptographic techniques and oblivious transfer to jointly compute a function of their private data [8, 78].”
BackgroundFederated Learning for Healthcare Informatics
Xu, J., Glicksberg, B. S., Su, C., Walker, P., Bian, J., & Wang, F. (2019) · arXiv · doi:10.48550/arxiv.1911.06270 · Cited by 1,538
“In this part, all users follow the protocol honestly, but the server may attempt to learn extra information in different ways [13].”
BackgroundMethodConvergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498
“To solve this issue, Secure Aggregation protocol is proposed in [222] to achieve the robustness of tolerating up to one-third devices failing to timely process the local training or upload the updates.”
MethodHow to backdoor federated learning
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1807.00459 · Cited by 1,495
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., & He, B. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3124599 · Cited by 1,407
“One can adopt differential privacy [38], [56], [120] to inject random noises into the parameters or use SMC [20], [21], [66] to”
BackgroundMethodDeep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Perez-Cruz, F. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134012 · Cited by 1,377
“directly without transferring sensitive data to the company’s data centers [8, 49].”
BackgroundMethodSattler, F., Muller, K.-R., & Samek, W. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3015958 · Cited by 1,355
Liang, J., Hu, D., & Feng, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.08546 · Cited by 1,241
“A common usage of FL consumes a simple aggregate of updates from multiple local users for the learning algorithm at the server-side (Bonawitz et al., 2017; McMahan et al., 2018), offering a privacy-preserving mechanism.”
BackgroundFederated learning on non-IID data: A survey
Zhu, H., Xu, J., Liu, S., & Jin, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.098 · Cited by 1,062
A Hybrid Approach to Privacy-Preserving Federated Learning
Truex, S., Baracaldo, N., Anwar, A., Steinke, T., Ludwig, H., Zhang, R., & Zhou, Y. (2019) · Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/3338501.3357370 · Cited by 1,029
FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
Chen, Y., Qin, X., Wang, J., Yu, C., & Gao, W. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.2988604 · Cited by 1,005
Optimizing Federated Learning on Non-IID Data with Reinforcement Learning
Wang, H., Kaplan, Z., Niu, D., & Li, B. (2020) · IEEE INFOCOM 2020 - IEEE Conference on Computer Communications · doi:10.1109/infocom41043.2020.9155494 · Cited by 981
“[3] developed a secure aggregation protocol that enables a server to perform the computation of high-dimensional data from the devices, which is widely deployed in production environments [4, 17].”
BackgroundLEAF: A Benchmark for Federated Settings
Caldas, S., Duddu, S. M. K., Wu, P., Li, T., Konečný, J., McMahan, H. B., Smith, V., & Talwalkar, A. (2018) · arXiv · doi:10.48550/arxiv.1812.01097 · Cited by 894
“Privacy and Security: Finally, the sensitive nature of personally-generated data requires methods that operate on federated data to balance privacy and security concerns with more traditional considerations such as statistical accuracy, scalability, and efficiency [24, 4].”
MethodSelf-citationFederated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges
Khan, L. U., Saad, W., Han, Z., Hossain, E., & Hong, C. S. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3090430 · Cited by 892
A survey on federated learning: challenges and applications
Wen, J., Zhang, Z., Lan, Y., Cui, Z., Cai, J., & Zhang, W. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01647-y · Cited by 883
“…robust reversible image watermarking scheme [37] Protect the private information of specific location in privacy-aware indoor location application [38] Can securely aggregate the clients’ parameters in FL [39] Propose a novel privacy gradient aggregation scheme using random matrix coding and…”
BackgroundMethodBeyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Wang, Z., Song, M., Zhang, Z., Song, Y., Wang, Q., & Qi, H. (2019) · IEEE INFOCOM 2019 - IEEE Conference on Computer Communications · doi:10.1109/infocom.2019.8737416 · Cited by 881
Deep Learning for Cardiac Image Segmentation: A Review
Chen, C., Qin, C., Qiu, H., Tarroni, G., Duan, J., Bai, W., & Rueckert, D. (2020) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2020.00025 · Cited by 869
Salem, A., Zhang, Y., Humbert, M., Berrang, P., Fritz, M., & Backes, M. (2019) · Proceedings 2019 Network and Distributed System Security Symposium · doi:10.14722/ndss.2019.23119 · Cited by 852
Verifynet: Secure and verifiable federated learning
Xu, G., Li, H., Liu, S., Yang, K., & Lin, X. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2929409 · Cited by 839
“Therefore, the security of Pseudorandom Generator [11] ensures that this hybrid is indistinguishable from the real protocol. hyb 5 In this hybrid, for each user n in the set U ∗ , the simulator generates the masked input as below : Since PRG (β n ) has been changed in the previous hybrid with a…”
BackgroundMethodResultInfluentialRobust Aggregation for Federated Learning
Pillutla, K., Kakade, S. M., & Harchaoui, Z. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3153135 · Cited by 801
“In practice, a secure average oracle is implemented using cryptographic protocols based on secure multi-party computation [13, 17].”
BackgroundMethodInfluentialAbdulrahman, S., Tout, H., Ould-Slimane, H., Mourad, A., Talhi, C., & Guizani, M. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3030072 · Cited by 796
“The work in [110] emphasizes on the need of computing multiparty aggregation, in which none of the participants reveals its update, not only among each other but also to the aggregator.”
BackgroundA Survey on Federated Learning for Resource-Constrained IoT Devices
Imteaj, A., Thakker, U., Wang, S., Li, J., & Amini, M. H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3095077 · Cited by 774
“Alternatively, such decisions can be made by a leader client, through a collaborative consensus scheme [56], [59], [83].”
Algorithmic fairness in artificial intelligence for medicine and healthcare
Chen, R. J., Wang, J. J., Williamson, D. F. K., Chen, T. Y., Lipkova, J., Lu, M. Y., Sahai, S., & Mahmood, F. (2023) · Nature Biomedical Engineering · doi:10.1038/s41551-023-01056-8 · Cited by 750
“This arises because of the sometimes-vast differences in local-data distribution at contributing sites, which can lead to the divergence of local model weights during training following synchronized initiation 204,247–249 .”
BackgroundFederated Learning: A Survey on Enabling Technologies, Protocols, and Applications
Aledhari, M., Razzak, R., Parizi, R. M., & Saeed, F. (2020) · IEEE Access · doi:10.1109/access.2020.3013541 · Cited by 733
SplitFed: When Federated Learning Meets Split Learning
Thapa, C., Mahawaga Arachchige, P. C., Camtepe, S., & Sun, L. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20825 · Cited by 720
Applied Federated Learning: Improving Google Keyboard Query Suggestions
Yang, T., Andrew, G., Eichner, H., Sun, H., Li, W., Kong, N., Ramage, D., & Beaufays, F. (2018) · arXiv · doi:10.48550/arxiv.1812.02903 · Cited by 684
“With secure aggregation [11], clients’ updates are securely summed into a single aggregate update without revealing any client’s individual component even to the server.”
BackgroundSelf-citationSecureBoost: A Lossless Federated Learning Framework
Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., & Yang, Q. (2021) · IEEE Intelligent Systems · doi:10.1109/mis.2021.3082561 · Cited by 669
“Recently, Google introduced a federated learning framework to prevent the data from being transmitted by bringing the model training to each mobile terminal [9], [10], [19].”
BackgroundMethodSecureBoost: A Lossless Federated Learning Framework
Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., & Yang, Q. (2019) · arXiv · doi:10.48550/arxiv.1901.08755 · Cited by 668
“Recently, Google introduced a federated learning framework to prevent the data from being transmitted by bringing the model training to each mobile terminal [9], [10], [19].”
BackgroundMethodA secure federated transfer learning framework
Liu, Y., Kang, Y., Xing, C., Chen, T., & Yang, Q. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.2988525 · Cited by 645
Secure Federated Transfer Learning
Liu, Y., Kang, Y., Xing, C., Chen, T., & Yang, Q. (2018) · arXiv · doi:10.48550/arxiv.1812.03337 · Cited by 645
Yin, X., Zhu, Y., & Hu, J. (2022) · ACM Computing Surveys · doi:10.1145/3460427 · Cited by 638
“It has been widely used in many PPFL methods [13, 125, 127, 144, 157, 164, 199, 227].”
BackgroundMethodInfluentialLabel-Only Membership Inference Attacks
Choquette-Choo, C. A., Tramèr, F., Carlini, N., & Papernot, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.14321 · Cited by 96
“Models trained with differential-privacy guarantees [19, 20, 21, 22] appear to effectively minimize the amount of membership leakage for all users, even when the formal privacy bounds are close to meaningless (i.”
BackgroundDiez-Olivan, A., Del Ser, J., Galar, D., & Sierra, B. (2019) · Information Fusion · doi:10.1016/j.inffus.2018.10.005 · Cited by 633
Flower: A Friendly Federated Learning Research Framework
Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Fernandez-Marques, J., Gao, Y., Sani, L., Li, K. H., Parcollet, T., de Gusmão, P. P. B., et al. (2020) · arXiv · doi:10.48550/arxiv.2007.14390 · Cited by 622
“Secure aggregation [23] is a way to hide model updates from “honest but curious” attackers.”
BackgroundDeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-based Incentive
Weng, J., Weng, J., Zhang, J., Li, M., Zhang, Y., & Luo, W. (2019) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2019.2952332 · Cited by 610
“been around in the past few years [8], [9], [10], [11], [12], [13], [14], [15], [16].”
BackgroundFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · arXiv · doi:10.48550/arxiv.1902.04885 · Cited by 600
“SMC provides formal privacy proof for these protocols [25].”
BackgroundInfluentialFederated learning for healthcare: Systematic review and architecture proposal
Antunes, R. S., André da Costa, C., Küderle, A., Yari, I. A., & Eskofier, B. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3501813 · Cited by 595
“[70] explore the use of secret sharing to secure model parameters before transmitting local models to collaborating parties.”
BackgroundModel Pruning Enables Efficient Federated Learning on Edge Devices
Jiang, Y., Wang, S., Valls, V., Ko, B. J., Lee, W.-H., Leung, K. K., & Tassiulas, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3166101 · Cited by 589
“Our adaptive pruning method is uniquely based on gradient information, which does not require sharing clients’ local data, so that existing privacy preservation and secure aggregation [40] methods for FL can be directly applied to the gradient.”
MethodChen, Y., Sun, X., & Jin, Y. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2953131 · Cited by 573
“In [17], Bonawitz et al. designed an efficient and robust transfer protocol for secure aggregation of high-dimensional data.”
BackgroundEfficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence
Hao, M., Li, H., Luo, X., Xu, G., Yang, H., & Liu, S. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2945367 · Cited by 569
“Table I lists the functional comparison of the latest privacy-preserving FL schemes, including PDL [19], PSA [20], and 4 [Online].”
BackgroundMethodPrivacy and Robustness in Federated Learning: Attacks and Defenses
Lyu, L., Yu, H., Ma, X., Chen, C., Sun, L., Zhao, J., Yang, Q., & Yu, P. S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3216981 · Cited by 548
“That is, no party learns anything more than the sum of the inputs of a subset of honest users of a large size [5].”
BackgroundMethodInfluentialA Field Guide to Federated Optimization
Wang, J., Charles, Z., Xu, Z., Joshi, G., McMahan, H. B., y Arcas, B. A., Al-Shedivat, M., Andrew, G., Avestimehr, S., Daly, K., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.06917 · Cited by 155
Self-citationSplit learning for health: Distributed deep learning without sharing raw patient data
Vepakomma, P., Gupta, O., Swedish, T., & Raskar, R. (2018) · arXiv · doi:10.48550/arxiv.1812.00564 · Cited by 513
Wahab, O. A., Mourad, A., Otrok, H., & Taleb, T. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3058573 · Cited by 487
“For example, the authors of [166] propose an SMC”
BackgroundXu, J., & Wang, H. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3031503 · Cited by 466
Machine Learning with Membership Privacy using Adversarial Regularization
Nasr, M., Shokri, R., & Houmansadr, A. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243855 · Cited by 458
“These methods leverage various techniques including homomorphic encryption, garbled circuits, and secure multi-party computation for private machine learning on encrypted data [8, 20, 33, 37], as well as private computation using trusted hardware (e.g., Intel SGX) [26, 39].”
MethodWhen Machine Learning Meets Privacy: A Survey and Outlook
Liu, B., Ding, M., Shaham, S., Rahayu, W., Farokhi, F., & Lin, Z. (2022) · ACM Computing Surveys · doi:10.1145/3436755 · Cited by 455
“scation DP-FedAvg Distributed [179] ✓ Obfuscation Training data obfuscation Centralised [121] ✓ Aggregation/Obfuscation DP+Aggregation Distributed [69,94] ✓ Aggregation Federated learning Distributed [12] ✓ Aggregation/Encryption Federated learning + SMC Distributed [118] ✓ Aggregation PATE Centralised [34] ✓ Aggregat…”
BackgroundMethodDifferential Privacy for Deep and Federated Learning: A Survey
Ouadrhiri, A. E., & Abdelhadi, A. (2022) · IEEE Access · doi:10.1109/access.2022.3151670 · Cited by 445
Lyu, L., Yu, H., Zhao, J., & Yang, Q. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_1 · Cited by 444
Privacy-Preserving Machine Learning: Threats and Solutions
Al-Rubaie, M., & Chang, J. M. (2019) · IEEE Security & Privacy · doi:10.1109/msec.2018.2888775 · Cited by 444
See through Gradients: Image Batch Recovery via GradInversion
Yin, H., Mallya, A., Vahdat, A., Alvarez, J. M., Kautz, J., & Molchanov, P. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01607 · Cited by 440
“We hope that future work can study vulnerabilities of aggregration-based federated learning [2], as well as further strengthen them to prevent inversion.”
BackgroundSecure Single-Server Aggregation with (Poly)Logarithmic Overhead
Bell, J. H., Bonawitz, K. A., Gascón, A., Lepoint, T., & Raykova, M. (2020) · Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3372297.3417885 · Cited by 438
“[8] uses the server as a relay that forwards encrypted and authenticated messages between clients.”
BackgroundResultInfluentialSelf-citationLDP-Fed: federated learning with local differential privacy
Truex, S., Liu, L., Chow, K.-H., Gursoy, M. E., & Wei, W. (2020) · Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and Networking · doi:10.1145/3378679.3394533 · Cited by 435
“Existing solutions to protect FL systems from such privacy attacks require trusted aggregators [17] or heavy cryptographic techniques [6, 23] which do not allow individual participants to define different local privacy guarantees, are insufficient for meaning-fully protecting each high dimensional…”
BackgroundLOGAN: Membership Inference Attacks Against Generative Models
Hayes, J., Melis, L., Danezis, G., & De Cristofaro, E. (2019) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2019-0008 · Cited by 433
“Privacy-enhancing tools based on secure multiparty computation and homomorphic encryption have been proposed to securely train supervised machine learning models, such as decision trees [36], linear regressors [15], and neural networks [9, 14].”
MethodSelf-Balancing Federated Learning With Global Imbalanced Data in Mobile Systems
Duan, M., Liu, D., Chen, X., Liu, R., Tan, Y., & Liang, L. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.3009406 · Cited by 432
“Recent research on federated learning has focused on reducing communication overhead [9], [10], [26], [27] and protecting privacy [28], [29], [30], [31], but only a few studies have noticed the problem of accuracy degradation due to imbalance [15], [32], [33].”
BackgroundPrivacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning
Fang, H., & Qian, Q. (2021) · Future Internet · doi:10.3390/fi13040094 · Cited by 424
“Based on privacy protection, machine learning with multi-party privacy protection could help users of all parties to jointly learn with each other’s data, on the premise of ensuring the security of their own data [1–3].”
BackgroundPrivacy‐preserving federated learning based on multi‐key homomorphic encryption
Ma, J., Naas, S., Sigg, S., & Lyu, X. (2022) · International Journal of Intelligent Systems · doi:10.1002/int.22818 · Cited by 421
“The scheme of secure aggregation has been adapted for federated learning, for instance, in [31, 32], to ensure that globally, an individual update from any distributed party can not be derived from the aggregation of all updates.”
MethodOort: Efficient Federated Learning via Guided Participant SelectionPreprint
Lai, F., Zhu, X., Madhyastha, H. V., & Chowdhury, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.06081 · Cited by 420
“Recent efforts in FL have been focusing on improving communication effi-ciency [38,55] or compression schemes [14], ensuring privacy by leveraging multi-party computation (MPC) [21] and differential privacy [31], or tackling heterogeneity by reinventing ML algorithms [50,70].”
BackgroundAsynchronous Federated Optimization
Xie, C., Koyejo, S., & Gupta, I. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.03934 · Cited by 410
“Federated learning is also motivated by the desire for privacy preservation [1, 2].”
BackgroundAttack of the tails: Yes, you really can backdoor federated learning
Wang, H., Sreenivasan, K., Rajput, S., Vishwakarma, H., Agarwal, S., Sohn, J.-Y., Lee, K., & Papailiopoulos, D. (2020) · arXiv · doi:10.48550/arxiv.2007.05084 · Cited by 406
“, a secure version of model averaging [26].”
BackgroundMachine Learning at the Network Edge: A Survey
Murshed, M. G. S., Murphy, C., Hou, D., Khan, N., Ananthanarayanan, G., & Hussain, F. (2022) · ACM Computing Surveys · doi:10.1145/3469029 · Cited by 402
“Techniques derived from cryptography can be applied for hiding updates of local devices from a central aggregation server [17] and also for hiding the aggregated update from the local devices [44].”
MethodPrivacy preservation in federated learning: An insightful survey from the GDPR perspective
Truong, N., Sun, K., Wang, S., Guitton, F., & Guo, Y. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102402 · Cited by 399
“Federated Averaging) can be protected 10 VOLUME 4, 2016 N. Truong et al.: Privacy Preservation in Federated Learning based on SMC called Secure Aggregation protocol, first proposed by Bonawitz in [9], [10]. The baseline of the protocol is SMC in which cryptography techniques are leveraged that enable participants to jo…”
BackgroundMethodInfluentialA state-of-the-art survey on solving non-IID data in Federated Learning
Ma, X., Zhu, J., Lin, Z., Chen, S., & Qin, Y. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.05.003 · Cited by 399
Thapa, C., & Camtepe, S. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.104130 · Cited by 393
“Thirdly, the updated model parameters are sent to the coordinating server, which aggregates those updates securely by using secure aggregation protocols [198] without learning individual inputs from the devices.”
MethodMitigating Sybils in Federated Learning Poisoning
Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2018) · arXiv · doi:10.48550/arxiv.1808.04866 · Cited by 385
“For example, differentially private [15] and securely aggregated [10] additions have been released; however, the use of federated learning in multi-party settings still presents new privacy and security vulnerabilities [19], [3].”
BackgroundImproving Federated Learning Personalization via Model Agnostic Meta Learning
Jiang, Y., Konečný, J., Rush, K., & Kannan, S. (2019) · arXiv · doi:10.48550/arxiv.1909.12488 · Cited by 381
“Successful algorithmic extensions to the central idea include training a differential private model (McMahan et al., 2018), compression (Koneˇcn´y et al., 2016b; Caldas et al., 2018a), secure aggregation (Bonawitz et al., 2017), and a smaller number of always-participating nodes (Yang et al., 2019).”
BackgroundMethodProchlo: Strong Privacy for Analytics in the Crowd
Bittau, A., Erlingsson, Ú., Maniatis, P., Mironov, I., Raghunathan, A., Lie, D., Rudominer, M., Kode, U., Tinnes, J., & Seefeld, B. (2017) · Proceedings of the 26th Symposium on Operating Systems Principles · doi:10.1145/3132747.3132769 · Cited by 378
“Other cryptography-based privacy-protection systems, such as PDDP, Prio, and Secure Aggregation [11, 15, 18], mostly share ESA’s goals but differ greatly in their approach.”
BackgroundHomomorphic Encryption-Based Privacy-Preserving Federated Learning in IoT-Enabled Healthcare System
Zhang, L., Xu, J., Vijayakumar, P., Sharma, P. K., & Ghosh, U. (2023) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3185327 · Cited by 376
Accelerating Federated Learning via Momentum Gradient Descent
Liu, W., Chen, L., Chen, Y., & Zhang, W. (2020) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.2975189 · Cited by 374
“For security aggregation of high-dimensional data, the work in [20] provided a communication-efficient approach, where the server can compute the sum of model parameters from edge nodes without knowing the contribution of each individual node.”
ShieldFL: Mitigating Model Poisoning Attacks in Privacy-Preserving Federated Learning
Ma, Z., Ma, J., Miao, Y., Li, Y., & Deng, R. H. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3169918 · Cited by 371
A Survey on ChatGPT: AI–Generated Contents, Challenges, and Solutions
Wang, Y., Pan, Y., Yan, M., Su, Z., & Luan, T. H. (2023) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2023.3300321 · Cited by 368
“By leveraging differential privacy [56], secure aggregation [57], or homomorphic encryption [58] techniques, the threats of data reconstruction attacks in federated AIGC model training can be mitigated.”
BackgroundBiscotti: A blockchain system for private and secure federated learning
Shayan, M., Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.3044223 · Cited by 354
“…have individually been defended in prior work through centralized anomaly detection [21], differential privacy [22], [23], [24], [25] or secure aggregation [26], [27], but to the best of our knowledge, a private and decentralized solution that solves both threats concurrently does not yet exist.”
BackgroundPrivacy-Enhanced Federated Learning Against Poisoning Adversaries
Liu, X., Li, H., Xu, G., Chen, Z., Huang, X., & Lu, R. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3108434 · Cited by 351
“SMC realizes private and correct computation through multiple interactions between participants [13], [14].”
BackgroundMethodCan You Really Backdoor Federated Learning?
Sun, Z., Kairouz, P., Suresh, A. T., & McMahan, H. B. (2019) · arXiv · doi:10.48550/arxiv.1911.07963 · Cited by 348
“Model update poisoning attacks are even harder to counter when secure aggregation (SecAgg) (7), which ensures that the server cannot inspect each user’s update, is deployed in the aggregation of local updates.”
BackgroundSelf-citationFederated Learning in Edge Computing: A Systematic Survey
Abreha, H. G., Hayajneh, M., & Serhani, M. A. (2022) · Sensors · doi:10.3390/s22020450 · Cited by 342
“Differential Privacy (DP) and secure aggregation approaches are the two most common methods to mitigate privacy issues in FL [104].”
BackgroundMethodSalvaging Federated Learning by Local Adaptation
Yu, T., Bagdasaryan, E., & Shmatikov, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.04758 · Cited by 60
“Secure aggregation (Bonawitz et al., 2017) prevents the global server from observing individual updates, but it also makes attacks on integrity impossible to detect and the final model may still leak training data.”
BackgroundFjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered DropoutPreprint
Horváth, S., Laskaridis, S., Almeida, M., Leontiadis, I., Venieris, S. I., & Lane, N. D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.13451 · Cited by 336
Cyber security meets artificial intelligence: a survey
Li, J.-H. (2018) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1800573 · Cited by 329
HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning
Xu, R., Baracaldo, N., Zhou, Y., Anwar, A., & Ludwig, H. (2019) · Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/3338501.3357371 · Cited by 327
“} {pk, sk} p1 pn (1-2) (8-9) (3) (4) (5) .”
BackgroundInfluentialTiFL: A Tier-based Federated Learning System
Chai, Z., Ali, A., Zawad, S., Truex, S., Anwar, A., Baracaldo, N., Zhou, Y., Ludwig, H., Yan, F., & Cheng, Y. (2020) · Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing · doi:10.1145/3369583.3392686 · Cited by 324
“A coordinator is responsible for creating and deploying a master aggregator and multiple child aggregators for achieving scalability as the real world cross-device FL system can involve up to 1010 clients [5, 18, 22].”
BackgroundMethodInfluentialFedMCCS: Multicriteria Client Selection Model for Optimal IoT Federated Learning
Abdulrahman, S., Tout, H., Mourad, A., & Talhi, C. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3028742 · Cited by 320
“Once Google invented FL, different related aspects have been advanced in the field of models aggregation [2], [6], [7], applications [8]–[10], privacy [11]–[13], security [14]–[16],”
BackgroundBlockchain-Based Federated Learning for Securing Internet of Things: A Comprehensive Survey
Issa, W., Moustafa, N., Turnbull, B., Sohrabi, N., & Tari, Z. (2023) · ACM Computing Surveys · doi:10.1145/3560816 · Cited by 319
“For example, Bonawitz et al. [20] and Gao et al. [46] employed a secret sharing mechanism to design FL frameworks that are able to preserve the participant’s privacy.”
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.