Byzantine-Resilient Secure Federated Learning
Open accessThe DOI matches its Crossref record; 47 of the 48 references it cites were found in a registry or an index.
Abstract
Secure federated learning is a privacy-preserving framework to improve machine learning models by training over large volumes of data collected by mobile users. This is achieved through an iterative process where, at each iteration, users update a global model using their local datasets. Each user then masks its local update via random keys, and the masked models are aggregated at a central server to compute the global model for the next iteration. As the local updates are protected by random masks, the server cannot observe their true values. This presents a major challenge for the resilience of the model against adversarial (Byzantine) users, who can manipulate the global model by modifying their local updates or datasets. Towards addressing this challenge, this paper presents the first single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning. BREA is based on an integrated stochastic quantization, verifiable outlier detection, and secure model aggregation approach to guarantee Byzantine-resilience, privacy, and convergence simultaneously. We provide theoretical convergence and privacy guarantees and characterize the fundamental trade-offs in terms of the network size, user dropouts, and privacy protection. Our experiments demonstrate convergence in the presence of Byzantine users, and comparable accuracy to conventional federated learning benchmarks.
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
“Bayesian neural networks [419] have been proposed and shown to be far more robust to over-fitting, and can easily learn from small datasets.”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [419]
In the citing paper
“To simultaneously preserve privacy for individual users while tolerating Byzantine adversaries, a Byzantine-resilient secure aggregation framework was developed in [171] to detect adversarial models without the knowledge of individual local models, as they are masked for privacy guarantees.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [171]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
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
Shamir, A. (1979) · Communications of the ACM · doi:10.1145/359168.359176 · Cited by 13,756 · cited 5×
“Our framework leverages Feldman’s verifiable secret sharing protocol from [17], which combines Shamir’s secret sharing [18] with homomorphic encryption.”
BackgroundMethodInfluentialAdvances 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
Federated 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
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956
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
Differential Privacy: A Survey of Results
Dwork, C. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79228-4_1 · Cited by 3,542 · cited 1×
“Although our focus is not on differential-privacy, our approach may in principle be combined with differential privacy techniques [27], which is an interesting future direction.”
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
Zhu, L., & Han, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_2 · Cited by 1,906
Distributed Systems: Concepts and Design
Coulouris, G., & Dollimore, J. (1988) · Cited by 1,629
On 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
(2017) · neural information processing systems · Cited by 1,413
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Yin, D., Chen, Y., Ramchandran, K., & Bartlett, P. (2018) · arXiv · doi:10.48550/arxiv.1803.01498 · Cited by 1,130 · cited 1×
“Existing works can be roughly classified into two main categories: 1) geometric median [9], [10] and 2) coordinate-wise median [11]–[13].”
BackgroundA practical scheme for non-interactive verifiable secret sharing
Feldman, P. (1987) · 28th Annual Symposium on Foundations of Computer Science (sfcs 1987) · doi:10.1109/sfcs.1987.4 · Cited by 1,125
Differentially Private Federated Learning: A Client Level Perspective
Geyer, R. C., Klein, T., & Nabi, M. (2017) · arXiv · doi:10.48550/arxiv.1712.07557 · Cited by 1,052
Beyond 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
QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
Alistarh, D., Grubic, D., Li, J., Tomioka, R., & Vojnović, M. (2016) · London School of Economics and Political Science Research Online (London School of Economics and Political Science) · doi:10.48550/arxiv.1610.02132 · Cited by 859
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
Fang, M., Cao, X., Jia, J., & Gong, N. Z. (2019) · arXiv · doi:10.48550/arxiv.1911.11815 · Cited by 828
Analyzing Federated Learning through an Adversarial Lens
Bhagoji, A. N., Chakraborty, S., Mittal, P., & Calo, S. (2018) · arXiv · doi:10.48550/arxiv.1811.12470 · Cited by 703
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
Authenticated Algorithms for Byzantine Agreement
Dolev, D., & Strong, H. R. (1983) · SIAM Journal on Computing · doi:10.1137/0212045 · Cited by 654
On-line Learning and Stochastic Approximations
Bottou, L. (1999) · On-Line Learning in Neural Networks · doi:10.1017/cbo9780511569920.003 · Cited by 564
Fair Resource Allocation in Federated Learning
Li, T., Sanjabi, M., Beirami, A., & Smith, V. (2020) · International Conference on Learning Representations · Cited by 512
Fair Resource Allocation in Federated Learning
Li, T., Sanjabi, M., Beirami, A., & Smith, V. (2019) · arXiv · doi:10.48550/arxiv.1905.10497 · Cited by 475
Secure 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
Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent
Chen, Y., Su, L., & Xu, J. (2017) · Proceedings of the ACM on Measurement and Analysis of Computing Systems · doi:10.1145/3154503 · Cited by 390
I Have a DREAM! (DiffeRentially privatE smArt Metering)
Ács, G., & Castelluccia, C. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-24178-9_9 · Cited by 388 · cited 1×
“In the non-Byzantine federated learning setting, secure aggregation is performed through a procedure known as additive masking [2], [21].”
MethodMohri, M., Sivek, G., & Suresh, A. T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00146 · Cited by 373
Li, L., Xu, W., Chen, T., Giannakis, G. B., & Ling, Q. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33011544 · Cited by 373
Can 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
Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning
So, J., Guler, B., & Avestimehr, A. S. (2021) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2021.3054610 · Cited by 318
Self-citationDistributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent
Chen, Y., Su, L., & Xu, J. (2018) · Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems · doi:10.1145/3219617.3219655 · Cited by 228
Inverting Gradients -- How easy is it to break privacy in federated learning?
Geiping, J., Bauermeister, H., Dröge, H., & Moeller, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.14053 · Cited by 195
Analyzing Federated Learning through an Adversarial Lens
Bhagoji, A. N., Chakraborty, S., Mittal, P., & Calo, S. B. (2019) · International Conference on Machine Learning · Cited by 188
Byzantine Stochastic Gradient Descent
Alistarh, D., Allen-Zhu, Z., & Li, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08917 · Cited by 163
A New Algorithm for Decoding Reed-Solomon Codes
Gao, S. (2003) · Springer eBooks · doi:10.1007/978-1-4757-3789-9_5 · Cited by 148
Byzantine-Tolerant Machine LearningPreprint
Blanchard, P., Mhamdi, E. M. E., Guerraoui, R., & Stainer, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.02757 · Cited by 137
Secure Byzantine-Robust Machine LearningPreprint
He, L., Karimireddy, S. P., & Jaggi, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04747 · Cited by 81
Federated Learning with Autotuned Communication-Efficient Secure Aggregation
Bonawitz, K., Salehi, F., Konečný, J., McMahan, B., & Gruteser, M. (2019) · 2019 53rd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/ieeeconf44664.2019.9049066 · Cited by 76
Performance Comparison of Secure Comparison Protocols
Kerschbaum, F., Biswas, D., & de Hoogh, S. J. A. (2009) · International Workshop on Database and Expert Systems Applications (DEXA) · doi:10.1109/dexa.2009.37 · Cited by 54
Byzantine-Resilient SGD in High Dimensions on Heterogeneous Data
Data, D., & Diggavi, S. N. (2021) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit45174.2021.9518248 · Cited by 46
Yang, H., Zhang, X., Fang, M., & Liu, J. (2019) · 2019 IEEE 58th Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9029245 · Cited by 40
Yang, H., Zhang, X., Fang, M., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.04532 · Cited by 8
(2020) · International Conference on Learning Representations
Research works printed but not linked: 3
- bottou, 1998, Online learning and stochastic approximations, Online Learning in Neural Networks, 17, 142
- mcmahan, 2017, Communication-efficient learning of deep networks from decentralized data, Proc 20th Int Conf Artif Intell Statist, 54, 1273
- lecun, 2010, MNIST Handwritten Digit Database
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
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
“Inspired by robust aggregation in Byzantine tolerant distributed learning [19], [157], where the number of tolerated Byzantine adversaries is used to evaluate the robustness, we”
MethodEdge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“To simultaneously preserve privacy for individual users while tolerating Byzantine adversaries, a Byzantine-resilient secure aggregation framework was developed in [171] to detect adversarial models without the knowledge of individual local models, as they are masked for privacy guarantees.”
MethodPrivacy-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
“The closest to our method we noticed is [22], as it focuses on making the current distance-based outlier removal mechanism compatible with secure aggregation utilizing SMC.”
MethodResultFedML: A Research Library and Benchmark for Federated Machine Learning
He, C., Li, S., So, J., Zeng, X., Zhang, M., Wang, H., Wang, X., Vepakomma, P., Singh, A., Qiu, H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13518 · Cited by 314
“To tackle the challenge of trustworthiness, existing research focuses on developing new defense techniques for adversarial attacks to make FL robust [15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 24, 27, 28], and proposing methods such as differential privacy (DP) and secure multiparty computation (SMPC) to protect…”
BackgroundSelf-citation
Metadata
- Authors
- So, J., Guler, B., & Avestimehr, A. S.
- Affiliations
- University of Southern California (US)
- Venue
- IEEE Journal on Selected Areas in Communications
- Published
- 2021-07
- Volume
- 39
- Issue
- 7
- Pages
- 2168-2181
- ISSN
- 0733-8716 (ISSN-L)
- 1558-0008
- OpenAlex
- W3107632872
- Cited by
- 313
- References
- 48
- Citations by year
- 2026: 32 · 2025: 81 · 2024: 67 · 2023: 55 · 2022: 43 · 2021: 27
- FWCI
- 13.06
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Journal on Selected Areas in Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Defense Advanced Research Projects Agency (HR001117C0053)
- Army Research Office (W911NF1810400)
- NSF (CCF-1703575, CCF-1763673)
- Office of Naval Research (N00014-16-1-2189)
- research gifts from Intel and Facebook
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Keywords
- secure federated learning, Byzantine resilience, secure aggregation, stochastic quantization, privacy preservation, convergence guarantees, user dropout
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.