Secure Distributed On-Device Learning Networks with Byzantine Adversaries
Open accessThe DOI matches its Crossref record; 15 of the 16 references it cites were found in a registry or an index.
Abstract
Privacy concerns exist when the central server has copies of datasets. Hence, there is a paradigm shift for learning networks to change from centralized in-cloud learning to distributed on-device learning. Benefitting from parallel computing, on-device learning networks have a lower bandwidth requirement than in-cloud learning networks. Moreover, on-device learning networks also have several desirable characteristics such as privacy preserving and flexibility. However, on-device learning networks are vulnerable to the malfunctioning terminals across the networks. The worst-case malfunctioning terminals are the Byzantine adversaries, that can perform arbitrary harmful operations to compromise the learned model based on the full knowledge of the networks. Hence, the design of secure learning algorithms becomes an emerging topic in the on-device learning networks with Byzantine adversaries. In this article, we present a comprehensive overview of the prevalent secure learning algorithms for the two promising on-device learning networks: Federated-Learning networks and decentralized-learning networks. We also review several future research directions in the Federated- Learning and decentralized-learning networks.
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
“the learned global model can be colluded by malicious attackers [40], [165]”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [40]
Citations
Cites
The Byzantine generals problem
Lamport, L., Shostak, R., & Pease, M. (1982) · ACM Transactions on Programming Languages and Systems · doi:10.1145/357172.357176 · Cited by 6,023 · cited 1×
“• Choose arbitrarily bad action from the full malicious action space to compromise the prediction accuracy of the networks [12].”
Background(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 4×
“proposed two aggregation rules [5]: component-wise median (CwMed) and component-wise trimmed mean (CwTM).”
BackgroundMethodInfluentialThe Hidden Vulnerability of Distributed Learning in Byzantium
Mhamdi, E. M. E., Guerraoui, R., & Rouault, S. (2018) · arXiv · doi:10.48550/arxiv.1802.07927 · Cited by 648
Federated Optimization:Distributed Optimization Beyond the Datacenter
Konečný, J., McMahan, B., & Ramage, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.03575 · Cited by 544
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
LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed LearningPreprint
Chen, T., Giannakis, G. B., Sun, T., & Yin, W. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09965 · Cited by 329
Distributed Optimization Under Adversarial Nodes
Sundaram, S., & Gharesifard, B. (2019) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2018.2836919 · Cited by 274
Distributed 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
Byzantine Stochastic Gradient Descent
Alistarh, D., Allen-Zhu, Z., & Li, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08917 · Cited by 163
Cited by
Edge 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
“…issue by keeping datasets locally, the shared model updates still cause extreme privacy leakage (e.g., model inversion attack), the learned global model can be colluded by malicious attackers [40], [165], and the edge devices may be adversarial at-tackers (e.g., data or model poisoning).”
BackgroundCommunication-efficient edge ai: algorithms and systems
Shi, Y., Yang, K., Jiang, T., Zhang, J., & Letaief, K. B. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3007787 · Cited by 488
Fraga-Lamas, P., Lopes, S. I., & Fernández-Caramés, T. M. (2021) · Sensors · doi:10.3390/s21175745 · Cited by 405
Hashemi, H., Wang, Y., & Annavaram, M. (2021) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1145/3466752.3480112 · Cited by 81
Shkalenko, A. V., & Nazarenko, A. V. (2024) · Risks · doi:10.3390/risks12060087 · Cited by 67
A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
Liu, Y., Zhang, L., Ge, N., & Li, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01973 · Cited by 50
Federated Learning of Unsegmented Chinese Text Recognition Model
Zhu, X., Wang, J., Hong, Z., Xia, T., & Xiao, J. (2019) · 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2019.00186 · Cited by 39
Fan, X., Wang, Y., Huo, Y., & Tian, Z. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3164339 · Cited by 43
Toward Smart Security Enhancement of Federated Learning Networks
Tan, J., Liang, Y.-C., Luong, N. C., & Niyato, D. (2021) · IEEE Network · doi:10.1109/mnet.011.2000379 · Cited by 42
“Median based methods (COMED, GEOMED, COTMED): aggregate model updates using median (or geometric median, trimmed median) values [7],[10] KRUM: use the most representative model update to update the global model [10] Preprocess model updates to with a bounded norm before the aggregation [14] RSA:…”
BackgroundMethodInfluentialRojek, I., Prokopowicz, P., Piechowiak, M., Kotlarz, P., Náprstková, N., & Mikołajewski, D. (2025) · Applied Sciences · doi:10.3390/app16010225 · Cited by 39
Byzantine-Resilient Federated Machine Learning via Over-the-Air Computation
Huang, S., Zhou, Y., Wang, T., & Shi, Y. (2021) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops50388.2021.9473694 · Cited by 31
Collective Learning: A 10-Year Odyssey to Human-centered Distributed Intelligence
Pournaras, E. (2020) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) · doi:10.1109/acsos49614.2020.00043 · Cited by 28
Dong, Y., Wang, L., Wang, J., Hu, X., Zhang, H., Yu, F. R., & Leung, V. C. M. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3329375 · Cited by 20
Self-citationTangle 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
“As in the centralized setting, a mechanism must ensure that updates received from the clients verifiably improve the quality of the overall model, while privacy of the training data is maintained [7].”
BackgroundSocialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems
Wang, X., Zhao, Y., Qiu, C., Hu, Q., & Leung, V. C. M. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3482978 · Cited by 17
Self-citationCommunication-Efficient Robust Federated Learning Over Heterogeneous DatasetsPreprint
Dong, Y., Giannakis, G. B., Chen, T., Cheng, J., Hossain, M. J., & Leung, V. C. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.09992 · Cited by 17
Self-citationArı, İ., Balkan, K., Pirbhulal, S., & Abie, H. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825993 · Cited by 10
Privacy Preserving Federated Learning Solution for Security of Industrial Cyber Physical Systems
Majidi, S. H., & Asharioun, H. (2021) · AI-Enabled Threat Detection and Security Analysis for Industrial IoT · doi:10.1007/978-3-030-76613-9_11 · Cited by 5
Anomaly-Aware Federated Learning with Heterogeneous Data
Chen, Z., Hu, C.-H., & Larsson, E. G. (2021) · IEEE International Conference on Autonomous Systems (ICAS) · doi:10.1109/icas49788.2021.9551122 · Cited by 4
Prototype-wise momentum-based federated contrast learning
Yong, Z., Zhang, J., Dong, Y., Liang, F., Li, A., & Hu, X. (2025) · Journal of Information and Intelligence · doi:10.1016/j.jiixd.2025.07.003 · Cited by 2
Self-citationIntelligent Spectrum Utilization: Challenges and Opportunities in Cognitive Radio Networks
Thakral, S., Verma, J., Ganage, S., Ganage, D., Monika, & Amalraj, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-06697-8_28 · Cited by 2
Mitra, D., Cortesi, A., & Chaki, N. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-41456-5_29 · Cited by 2
Joint Precoding and Power Control in Small-Cell Networks with Proportional-Rate MISO-BC Backhaul
Dong, Y., Hossain, M. J., Cheng, J., & Leung, V. C. M. (2019) · Globecom · doi:10.1109/globecom38437.2019.9014236 · Cited by 2
Self-citationUAV-Assisted Heterogeneous Federated Learning over the Air Against Byzantine Attacks
Fan, X., Li, G., Luo, C., Hong, Y., Chen, Z., Chen, T., & Huo, Y. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010167 · Cited by 1
A Momentum-Based Wireless Federated Learning Acceleration With Distributed Principle Decomposition
Dong, Y., Wang, L., Chi, Y., Hu, X., Zhang, H., Yu, F. R., & Leung, V. C. M. (2023) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw59220.2023.10193196 · Cited by 1
Self-citationA Byzantine-Robust Federated Learning with Nesterov MomentumPreprint
Xu, L., Fan, X., Wang, G., Zeng, R., Hu, X., & Dong, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.02657 · Cited by 1
Self-citationA Seesaw Model Attack Algorithm for Distributed Learning
Yang, K., Luo, T., Dong, Y., & Li, A. (2024) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot62235.2024.00025
Self-citationDefending Byzantine Failures for Federated Learning
Li, A., Xing, K., & Dong, Y. (2024) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot62235.2024.00035
Self-citationCol-TEEs: Secure and Efficient Collaborative Inference Framework in Heterogeneous TEEs
Liu, X., Li, T., Jian, Z., Xie, X., Li, M., & Wang, G. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11322922
Metadata
- Authors
- Dong, Y., Cheng, J., Hossain, M. J., & Leung, V. C. M.
- Affiliations
- University of British Columbia (CA)
- Venue
- IEEE Network
- Published
- 2019-11
- Volume
- 33
- Issue
- 6
- Pages
- 180-187
- ISSN
- 0890-8044 (ISSN-L)
- 1558-156X
- OpenAlex
- W2966325922
- Cited by
- 28
- References
- 16
- Citations by year
- 2025: 5 · 2024: 5 · 2023: 3 · 2022: 1 · 2021: 6 · 2020: 6 · 2019: 2
- FWCI
- 1.73
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Network (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Killam Trusts
- University of British Columbia
- Shenzhen University
- Natural Sciences and Engineering Research Council of Canada
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Keywords
- on-device learning, Byzantine adversaries, federated learning, decentralized learning, privacy preservation, model robustness, distributed learning
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.