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 1,001–1,036 of 1,036
Federated learning vulnerabilities, threats and defenses: A systematic review and future directions
Almutairi, S., & Barnawi, A. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100947 · Cited by 35
FORESEEN: Towards Differentially Private Deep Inference for Intelligent Internet of Things
Lyu, L., Bezdek, J. C., Jin, J., & Yang, Y. (2020) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3000374 · Cited by 34
“Similarly, for training data privacy in federated learning, Bonawitz et al. [16] proposed a secure aggregation protocol.”
BackgroundEavesdrop the Composition Proportion of Training Labels in Federated Learning
Wang, L., Xu, S., Wang, X., & Zhu, Q. (2019) · arXiv · doi:10.48550/arxiv.1910.06044 · Cited by 34
“Bonawitz et al. [28] design secure multi-party aggregation techniques, pertinent for federated learning, to enable participants to encrypt themselves so that the central server cannot observe individual gradient updates in the plain form and only do the aggregation operation.”
BackgroundHow to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning
Lyu, L., Li, Y., Nandakumar, K., Yu, J., & Ma, X. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2020.3006287 · Cited by 31
“Federated learning is a special case of distributed deep learning, which is tailored to deal with Non-IID, unbalanced and massively distributed data in mobile application [4], [5], [6].”
BackgroundMethodA federated learning architecture for secure and private neuroimaging analysis
Stripelis, D., Gupta, U., Saleem, H., Dhinagar, N., Ghai, T., Anastasiou, C., Sánchez, R., Steeg, G. V., Ravi, S., Naveed, M., et al. (2024) · Patterns · doi:10.1016/j.patter.2024.101031 · Cited by 31
Defending against Backdoors in Federated Learning with Robust Learning Rate
Ozdayi, M. S., Kantarcioglu, M., & Gel, Y. R. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i10.17118 · Cited by 30
Practical Attribute Reconstruction Attack Against Federated Learning
Chen, C., Lyu, L., Yu, H., & Chen, G. (2024) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2022.3159236 · Cited by 30
“Besides differential privacy, cryptology can also be used to prevent leakage: Bonawitz et al. [33] proposed a practical secure aggregation protocol, which is proved to be secure in the honest-but-curious and active adversary setting.”
MethodFederated inference and belief sharing
Friston, K. J., Parr, T., Heins, C., Constant, A., Friedman, D., Isomura, T., Fields, C., Verbelen, T., Ramstead, M., Clippinger, J., et al. (2024) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2023.105500 · Cited by 30
“…to distributed SGD, each party calculates gradients locally on parts of their dataset and shares only these with other parties, e.g., further secured by using secret sharing (Bonawitz et al., 2017), homomorphic encryption (Phong et al., 2018), or differential privacy (Shokri and Shmatikov, 2015).”
BackgroundPrivacy preserving and secure robust federated learning: A survey
Han, Q., Lu, S., Wang, W., Qu, H., Li, J., & Gao, Y. (2024) · Concurrency and Computation: Practice and Experience · doi:10.1002/cpe.8084 · Cited by 29
“Privacy Stealingdatainferringprivate informationcompromising modelconfidentialityand privacy 7–9 • Additivemasking 20–27 • Differentialprivacy: GDP 28–37 LDP 32,38–52 Hybrid-DP 53–67 • Homomorphicencryption 56,”
BackgroundSecure Federated Submodel Learning
Niu, C., Wu, F., Tang, S., Hua, L., Jia, R., Lv, C., Wu, Z., & Chen, G. (2019) · arXiv · doi:10.48550/arxiv.1911.02254 · Cited by 28
“only suffices for the recommendation models used in Alibaba but also can easily degenerate to a widely used vector-based representation [18], [30], by setting the number of columns d to 1.”
BackgroundMethodResultInfluentialPrivacy-Encoded Federated Learning Against Gradient-Based Data Reconstruction Attacks
Liu, H., Li, B., Gao, C., Xie, P., & Zhao, C. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3309095 · Cited by 27
Devi, M., Nandal, P., & Sehrawat, H. (2025) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2025.200553 · Cited by 27
Novikova, E., Fomichov, D., Kholod, I., & Filippov, E. (2022) · Sensors · doi:10.3390/s22082983 · Cited by 24
“Secure aggregation (SecAgg) [57] is a lightweight MPC protocol specifically designed for the FL settings and could be used in cross-device settings.”
BackgroundMethodInfluentialRobust federated learning with attack-adaptive aggregation
Wan, C. P. (2022) · doi:10.14711/thesis-991012994506603412 · Cited by 24
Backdoor Attacks on Federated Meta-Learning
Chen, C.-L., Golubchik, L., & Paolieri, M. (2020) · arXiv · doi:10.48550/arxiv.2006.07026 · Cited by 22
“Additional privacy threats have also been addressed in federated learning: for example, secure aggregation techniques have been proposed where users send encrypted updates that the server applies to an encrypted model [2, 3].”
Alahmari, S., & Alghamdi, I. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.107849 · Cited by 21
A comprehensive survey and taxonomy on privacy-preserving deep learning
Tran, A.-T., Luong, T.-D., & Huynh, V.-N. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127345 · Cited by 21
Efficient Federated Matrix Factorization Against Inference Attacks
Chai, D., Wang, L., Chen, K., & Yang, Q. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3501812 · Cited by 20
“HE is not the only choice here and could be substituted by other privacy-preserving aggregation methods, e.g., SecureAggrega-tion [6].”
MethodPan, J., Fan, Z., Smith, G. E., Guo, Y., Bian, J., & Xu, J. (2025) · Alzheimer's & Dementia · doi:10.1002/alz.70128 · Cited by 19
Tangle Ledger for Decentralized Learning
Schmid, R., Pfitzner, B., Beilharz, J., Arnrich, B., & Polze, A. (2020) · 2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) · doi:10.1109/ipdpsw50202.2020.00144 · Cited by 17
“To prevent this type of privacy breach, federated learning research includes algorithms which use one or multiple middle-men between clients and server [24], [25], however, the requirement of trust between client and facilitator still stands.”
BackgroundDevice Heterogeneity in Federated Learning: A Superquantile Approach
Laguel, Y., Pillutla, K., Malick, J., & Harchaoui, Z. (2020) · arXiv · doi:10.48550/arxiv.2002.11223 · Cited by 15
Source-Free Unsupervised Domain Adaptation: A Survey
Fang, Y., Yap, P.-T., Lin, W., Zhu, H., & Liu, M. (2023) · arXiv · doi:10.48550/arxiv.2301.00265 · Cited by 15
“Federated learning [227]– [229] is a decentralized scheme to facilitate collaborative learning among multiple distributed clients without sharing training data or model parameters.”
BackgroundAramoon, O., Chen, P.-Y., Qu, G., & Tian, Y. (2024) · Federated Learning · doi:10.1016/b978-0-44-319037-7.00017-x · Cited by 12
Robust Federated Learning for Ubiquitous Computing through Mitigation of Edge-Case Backdoor Attacks
Elhattab, F., Bouchenak, S., Talbi, R., & Nitu, V. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3569492 · Cited by 11
“Furthermore, the FL server usually relies on secure aggregation, that is a secure multi-party computation protocol to compute the aggregated model in a privacy preserving manner, thus, preventing honest-but-curious servers from examining clients’ models [10].”
MethodFedNRM: A Federal Personalized News Recommendation Model Achieving User Privacy Protection
Yu, S., Jie, Z., Wu, G., Zhang, H., & Shen, S. (2023) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.039911 · Cited by 10
Zhang, L., Li, G., Yuan, L., Ding, X., & Rong, Q. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2023.103580 · Cited by 9
A Secure Cloud-Edge Collaborative Logistic Regression Model
Wang, C., Xu, J., & Yin, L. (2021) · 2021 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics53846.2021.00049 · Cited by 8
Cloud-based federated boosting for mobile crowdsensing
Wang, Z., Yang, Y., Liu, Y., Liu, X., Gupta, B. B., & Ma, J. (2020) · arXiv · doi:10.48550/arxiv.2005.05304 · Cited by 6
“[4] designed a universal and practical model aggregation scheme for mobile devices with secret sharing technology.”
BackgroundFedVPS: Federated Learning for Privacy and Security of Internet of Vehicles on Non-IID Data
Hangdong, K., Bo, M., Darong, H., & Zhaoyang, D. (2023) · 2023 IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls58216.2023.10166791 · Cited by 6
Woisetschläger, H., Mertel, S., Krönke, C., Mayer, R., & Jacobsen, H.-A. (2024) · arXiv · doi:10.48550/arxiv.2407.08105 · Cited by 1
“Private and secure computing techniques like Differential Privacy or Trusted Execution Environments help improve data privacy and system security (Bonawitz et al., 2017; Andrew et al., 2021).”
Securing Genomic Data Against Inference Attacks in Federated Learning Environments
Pathade, C., & Patil, S. (2025) · arXiv · doi:10.48550/arxiv.2505.07188 · Cited by 1
Panagoulias, D. P., Damian, A. I., Stamate, C., Toderian, V., Butusina, P., De Franceschi, A., Bleotiu, C., Sakkopoulos, E., & Tsichrintzi, E.-A. (2026) · Electronics · doi:10.3390/electronics15143046 · Cited by 1
Anomaly detection and root-cause identification in microservices: a survey
Barata, L. M., Sequeira, S., Lopes, E., Inácio, P. R. M., & Freire, M. M. (2026) · Cluster Computing · doi:10.1007/s10586-026-06095-9 · Cited by 4
“By combining local inference with trusted aggregation, TDAI can enhance both privacy and robustness of anomaly detection pipelines [239].”
Segar, N., & Vijayan, V. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1804943 · Cited by 5
“Privacy-preserving aggregation mechanisms, including secure aggregation and differential privacy integration, protect individual model updates from inference attacks (Bonawitz et al., 2017).”
On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Steps
Heikkilä, M. A. (2024) · arXiv · doi:10.48550/arxiv.2407.19286
Understanding Unintended Memorization in Federated Learning
Thakkar, O., Ramaswamy, S., Mathews, R., & Beaufays, F. (2020) · arXiv · doi:10.48550/arxiv.2006.07490
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.