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.”
Background
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
Items 201–300 of 316
Defending Federated Learning System from Poisoning Attacks via Efficient Unlearning
Cai, L. Z., Gu, K., & Lei, J. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.061377 · Cited by 4
Hamdi, A., Noura, H., & Azar, J. (2025) · Applied System Innovation · doi:10.3390/asi8050146 · Cited by 3
Gao, K., Zhu, T., Ye, D., Liu, B., & Zhou, W. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3630811 · Cited by 5
FORTA: Byzantine-Resilient FL Aggregation via DFT-Guided Krum
Shahul, U., & Harshan, J. (2025) · IEEE Information Theory Workshop (ITW) · doi:10.1109/itw62417.2025.11240545 · Cited by 2
“Recent works [7], [8] have explored secure aggregation techniques that integrate Byzantine resilience while preserving privacy.”
A Survey of Federated Learning: Advances in Architecture, Synchronization, and Security Threats
Mahmud, F., Mahmud, F., & Rahman, R. M. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.073519 · Cited by 8
Peng, C., & Xian, H. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104345 · Cited by 2
Dang, Q.-V., Vo, T.-B.-D., & Nguyen, N.-S.-A. (2026) · Array · doi:10.1016/j.array.2026.100680 · Cited by 3
Muazu, T., & Mao, Y. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112161 · Cited by 2
Kianpisheh, S., Taleb, T., Iinatti, J., & Song, J. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432263 · Cited by 2
“The robustness of FL against Byzantine clients while preserving privacy has been investigated in [9].”
Divergence-Based Adaptive Aggregation for Byzantine Robust Federated Learning
Xiao, B., Zhu, F., Zhang, J., Ni, W., & Wang, X. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3707437 · Cited by 4
“These attacks, commonly known as Byzantine attacks [4], [5], disrupt the global model training by tampering with the local data or model updates of the attacked workers, which seriously deteriorate training performance and system security.”
MPHM: Model poisoning attacks on federal learning using historical information momentum
Shi, L., Chen, Z., Shi, Y., Lin, W., Tao, Y., He, M., Wang, Q., Zhou, Y. H., & Gao, Y. (2023) · Security and Safety · doi:10.1051/sands/2023006 · Cited by 8
“Firstly, in the federated learning framework, the cloud server does not have access to the participant’s local data or training process, which means that malicious participants can upload incorrect model updates to corrupt the global model [16].”
BackgroundAchieving Provable Byzantine Fault-tolerance in a Semi-honest Federated Learning Setting
Tang, X., Gu, H., Fan, L., & Yang, Q. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-33377-4_32 · Cited by 2
Trustworthy Anti-Collusion Federated Learning Scheme Optimized by Game Theory
Li, Q., Zhou, Q., Li, M., & Wang, Z. (2023) · Electronics · doi:10.3390/electronics12183867 · Cited by 3
Networked Personalized Federated Learning Using Reinforcement Learning
Gauthier, F., Gogineni, V. C., & Werner, S. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279781 · Cited by 2
“Several challenges associated with the practical implementation of FL, such as communication efficiency [4], privacy preservation [5], byzan-tine attacks [6], and asynchronous behavior of devices and communication links [7], have been studied extensively in the literature.”
BackgroundPrivate Aggregate Queries to Untrusted Databases
Hafiz, S. M., Gupta, C., Wnuck, W., Vora, B., & Chuah, C. (2024) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2024.241211 · Cited by 2
“Pillutla et al. [37] and So et al. [38] attempt to solve the secure aggregation problem specifically in the setting of federated learning.”
BackgroundLOGSAFE: Logic-Guided Verification for Trustworthy Federated Time-Series Learning
Nguyen, D. T., An, Z., Johnson, T. T., Ma, M., & Leach, K. (2026) · ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS) · doi:10.1109/iccps68698.2026.00019 · Cited by 2
“The Byzantine attack is among the most popular such attacks [17], [37].”
Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learning
Xia, Y., Hofmeister, C., Egger, M., & Bitar, R. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3694660 · Cited by 3
“Therefore, users apply an element-wise stochastic quantizer Q q ( x ) with 2 q + 1 quantization intervals as in [25] and [26]: where q is the number of quantization levels.”
InfluentialChallenges, Opportunities, and Future Prospects
Abdel‐Basset, M., Moustafa, N., Hawash, H., & Ding, W. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-89025-4_10 · Cited by 2
Communication-efficient Federated Learning with an Event-triggering Strategy
Li, Y., Bai, J., Li, D., & Li, W. (2022) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls55054.2022.9858572 · Cited by 3
“Another research hot spot of federated learning is the Byzantine problem [25–29].”
Fedmpo : federated optimization based on multidimensional especially 3-dimensional proximal operator
Jiang, F., Yang, X., Li, Y., & Li, L. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01956-w · Cited by 2
“Despite that there are many excellent studies focus on distributed optimization in the context of FL [21–25], FL still distinguishes two key challenges from traditional distributed optimization, a high degree of system and statistical heterogeneity [26–35].”
Byzantine-Robust Privacy-Preserving Federated Learning Based on DT-PKC
Jiang, W., Fu, S., Luo, Y., Liu, L., & Wang, Y. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9331-4_14 · Cited by 3
Secure Submodel Aggregation for Resource-Aware Federated Learning
Sami, H. U., & Güler, B. (2024) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit57864.2024.10619575 · Cited by 1
“For the details of this transformation, we refer to [10], [21], [24], [25].”
BackgroundBalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning
Masuda, H., Kita, K., Koizumi, Y., Takemasa, J., & Hasegawa, T. (2024) · IEEE Access · doi:10.1109/access.2024.3491779 · Cited by 1
“Existing Byzantine-resilient secure aggregation protocols [36], [37], [38], [39] have a communication cost of O ( n 2 ), where n is the number of all users since each user sends one share of its local model to each other users like LightSecAgg.”
BackgroundA Survey on Securing Image-Centric Edge Intelligence
Li, T., Hu, H., Gabbouj, M., Ye, Q., Xiang, Y., Li, J., & Li, L. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3700792 · Cited by 4
Security and Credit evaluation mechanism federated learning privacy protection scheme
Guan, G., Zhi, T., Cai, Y., Cao, Y., Dong, H., & Zhou, W. (2025) · International Conference on Computer Research and Development · doi:10.1109/iccrd64588.2025.10963257 · Cited by 1
“To address this issue, relevant researchers have proposed a series of solutions [9]-[10] to make federated learning models more robust and secure.”
Enhancing Federated Learning Security with Reputation-Based Phishing Defense
Singh, A. (2025) · International Conference on Information and Computer Technologies (ICICT) · doi:10.1109/icict64582.2025.00049 · Cited by 1
Bendoukha, A.-A., Sirdey, R., Boudguiga, A., & Kaaniche, N. (2025) · IEEE Computer Security Foundations Workshop (CSFW) · doi:10.1109/csf64896.2025.00025 · Cited by 6
“Several solutions based on aggregating the updates using a median, or to discard updates based on their distance to an average [68, 69, 24], or directional shift from a barycentric gradient vector [25] were proposed to mitigate byzantine attacks against the FL learning process.”
Empowering Clients: Self-Adaptive Federated Learning for Data Quality Challenges
Talukder, Z., Rana, M., Hamm, K., & Islam, M. A. (2025) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge67623.2025.00023 · Cited by 1
Byzantine-resilient federated online learning for Gaussian process regression
Zhang, X., Yuan, Z., & Zhu, M. (2025) · Automatica · doi:10.1016/j.automatica.2025.112554 · Cited by 1
Li, Y., Li, X., Wan, H., & Wang, C. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-94445-1_1 · Cited by 1
A verifiable and efficient chained federated learning scheme for privacy protection
Wang, X., Liu, Z., Dai, M., Gong, J., & Ni, W. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111838 · Cited by 1
Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning
Egger, M., & Bitar, R. (2025) · IEEE Information Theory Workshop (ITW) · doi:10.1109/itw62417.2025.11240449 · Cited by 3
FBFL: Flexible Byzantine-Robust Federated Learning With Privacy-Preserving
Xu, Y., Zhang, H., Zhao, J., Gai, K., Tian, Z., & Yang, J. (2025) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2025.3641757 · Cited by 1
Fed-DPRoC: Communication-Efficient Differentially Private and Robust Federated Learning
Xia, Y., Jahani-Nezhad, T., & Bitar, R. (2025) · International Conference on Federated Learning Technologies and Applications (FLTA) · doi:10.1109/flta67013.2025.11336422 · Cited by 2
“…addressing two out of those three challenges is studied in the literature: Privacy and robustness are considered in, e.g., [11], [12], [18], [26]–[33]; communication efficiency and privacy are considered in, e.g., [14], [34]–[36]; and communication efficiency and robustness are studied in, e.g.,…”
Revisiting the Byzantine Resilience of Federated Reinforcement Learning: A Distillation Perspective
Jiang, W., Wang, J., Zhong, Z., Liao, J., Zhu, X., & Fan, F. X. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00013 · Cited by 1
“…stems from the limitations of the Federated Averaging (FedAVG) algorithm [7]: the attempt to balance the contributions of different clients creates opportunities for Byzantine clients to exploit, which has simultaneously driven research into Byzantine-resilient federated algorithms [17], [20]–[24].”
Privacy-Preserving and Poisoning-Resilient Enhanced Cross-Silo Federated Learning
Zheng, X., Yan, X., Yang, F., Ng, W. W. Y., Li, Y., & Wu, S. (2025) · International Conference on Blockchain Technology and Information Security (ICBCTIS) · doi:10.1109/icbctis66509.2025.11387244 · Cited by 1
“So et al. [19] integrates verifiable secret sharing with multi-Krum for Byzantine-resilient secure aggregation.”
TCFL: Trapdoor homomorphic encryption based federated learning aggregator with filter
Shen, X., Jia, Y., Xu, C. L., & Zhu, L. (2026) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-02193-4 · Cited by 1
Dual-Factor Adaptive Robust Aggregation for Secure Federated Learning in IoT Networks
Song, Z., Tan, W., Wang, H., Zhang, G., & Weng, J. (2026) · Future Internet · doi:10.3390/fi18040201 · Cited by 1
A Privacy-Preserving Federated Learning with Mutual Verification on Vector Spaces
Zhang, M., Cui, C., Shen, G., & Zhang, Y. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7242-3_14 · Cited by 1
FBL-BP: Byzantine-Resilient and Privacy-Preserving Federated Broad Learning
Cheng, S., & Ren, C. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10394524 · Cited by 2
“In [16], a distance-based outlier removal mechanism was chosen to be combined with a secret sharing protocol in Secure Multiparty Computing (SMC).”
MethodRIFL: A Fair Incentive Mechanism for Federated Learning
Tang, H., Liao, X., & Ouyang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5663-6_31 · Cited by 1
Privacy-Preserving and Robust Federated Learning Based on Secret Sharing
Mei, J., Shen, X., Xu, C. L., Zhu, L., Jin, G., & Sharif, K. (2024) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa63168.2024.00223 · Cited by 1
“In order to resist poisoning attacks in FL, many robust aggregation schemes have been proposed [6], [7], [8], [9], [10].”
Robust Federated Learning Against Model Perturbation in Edge Networks
Jin, D., Xiao, Y. L., & Li, Y. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161143 · Cited by 1
“First, computation and communication costs for defenses specialized for malicious perturbations may lead to a huge burden on the edge networks and compromise the learning efficiency [6].”
Inferring Communities of Interest in Collaborative Learning-based Recommender Systems
Belal, Y., Maouche, M., Mokhtar, S. B., & Simonet, A. (2025) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs63083.2025.00056 · Cited by 3
Privacy-Preserving Federated Learning Compatible with Robust AggregatorsPreprint
Alebouyeh, Z., & Bidgoly, A. J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4793556 · Cited by 2
Machine learning for road active safety in vehicular networks
Hao, J. (2024) · theses.fr (ABES) · doi:10.70675/e95f26b1ze81ez4c71z9826ze26e17831466 · Cited by 1
Optimization methods for collaborative learning
Karimireddy, S. P. (2021) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.5075/epfl-thesis-8056
2021 Index IEEE Journal on Selected Areas in Communications Vol. 39
(2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3132125
On the Fundamental Limits of Secure Summation and MDS Variable Generation
Zhao, Y. (2023) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc2179290
Adaptive Distributed Learning with Byzantine Robustness: A Gradient-Projection-Based Method
Wang, X., Huang, C., Ning, J., Yang, T., & Shen, X. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437165
“This paradigm exhibits greater scalability compared to federated learning, making it particularly suitable for application scenarios where a centralized server is not feasible [1].”
BackgroundPrivacy-Preserving Federated Learning for Brain MRI Analysis
Dcunha, L., Dsouza, L., Ramanan, G., & Chaudhari, S. (2023) · International Conference on Recent Trends in Advance Computing (ICRTAC) · doi:10.1109/icrtac59277.2023.10480812
“[2] The authors delve into recent research studies that have leveraged Federated Learning (FL) for the analysis of medical images, encompassing various imaging modalities such as MRI, CT scans, and ultrasound [3].”
BackgroundPrivacy-Preserving Federated Learning Compatible with Robust AggregatorsPreprint
Alebouyeh, Z., & Bidgoly, A. J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4882102 · Cited by 1
Sparsity-Based Secure Gradient Aggregation for Resource-Constrained Federated Learning
Sami, H. U., & Güler, B. (2024) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit57864.2024.10619102
“For the details of this transformation, we refer to [11], [26], [29], [30].”
BackgroundRobust Secure Aggregation for Co-located IoT Devices with Corruption Localization
Crescenzo, G. D., van Kempen, E., & Tsudik, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-76934-4_3
Fed-BRMC: Byzantine-Robust Federated Learning via Dual-Model Contrastive Detection
Gan, X., Lü, P., Gan, S., Xian, Y., Peng, K., Liu, P., & Li, D. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831005
“…Guilin, China * indicates the corresponding author Byzantine attacks in FL, primarily based on clustering and statistical knowledge [5], [8], [20], [23], [24], are effective in independent and identically distributed (IID) settings but face limitations in non-independent and identically…”
FedSV: A Privacy-Preserving Byzantine-Robust Federated Learning Scheme with Self-validation
Jiang, W., Fu, S., Luo, Y., Liu, L., & Wang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-1525-4_13
VeriTrac: Verifiable and traceable cross-silo federated learning
Xu, Y., Zhang, H., Liu, Z., Gao, F., & Qiao, L. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.107780
An Asynchronous Robust Federated Learning Approach for Data Value in IoT
Liang, H., Jin, M., Yan, H., Han, S., Li, W., Yang, Z., & Wang, Z. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2468-3_20
Information‐Theoretically Private Federated Submodel Learning With Byzantine Local Updates
Kim, M., & Hong, S. (2025) · Electronics Letters · doi:10.1049/ell2.70268
Federated Learning: An Overview of Attacks and Defense Methods
Sameera, K. M., Arikkat, D. R., Vinod, P., A., R. R. K., Aneez, A., & Conti, M. (2025) · Springer eBooks · doi:10.1007/978-3-031-83157-7_14 · Cited by 2
Resilient Distributed Optimization
Kuwaranancharoen, K., Xin, L., & Sundaram, S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-14081-5.00072-6
Secure Embedding Aggregation for Cross-Silo Federated Representation Learning
Li, S., Tang, J., Zhu, J., Zhang, K., Sun, L., & Dong, C. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3580228
“We focus on standard semi-honest threat model, a prevalent assumption in the Federated Learning privacy literature for modeling both server and client adversaries [7], [10], [11], [26], [34].”
LBRFL: Lightweight Privacy-Preserving Federated Learning with Byzantine-Robustness
Shen, P., Zhao, S., Xu, J., Zhao, C., Chen, Z., & Guo, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6606-5_3
Wang, Y., Wang, H., Yao, Y., Jiao, Z., Zhou, L., & Wu, Y. (2025) · International Conference on Cyber Security, Artificial Intelligence and Digital Economy (CSAIDE) · doi:10.1145/3729706.3729780
“To prevent model parameters from being tampered with or leaked, techniques such as homomorphic encryption (HE) [ 8 ] , differential privacy (DP) [ 9 ] , and secret sharing [ 6 ] can be used to protect the security of model parameters.”
A Privacy-Preserving Federated Learning Framework with Byzantine Robustness
Zhang, X., & Shen, G. (2024) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc64274.2024.00182
“Existing studies [11-15] that address both privacy and robustness often compromise on efficiency, with some leaking intermediate values [14] or lacking robustness against attacks [12, 15].”
PARSIFAL: Private and Robust Sign Federated Learning
Lei, R., Wang, P., Zeng, J., Wang, C., Pei, H., & Zhao, J. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737074
Nosy Layers, Noisy Fixes: Tackling DRAs in Federated Learning Systems using Explainable AI
Nandi, M., Shaghaghi, A., Sultan, N. H., Batista, G., Zhao, R. K., & Jha, S. K. (2025) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3708821.3736188 · Cited by 1
Robust Federated Learning With Multi-Category Accuracy for Non-IID Data
Yang, Q., Xu, P., Yu, S., Huang, H., Wang, J., Liu, Y., Tian, Z., & Wu, C. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3597606
“Although the federated learning paradigm could guarantee the privacy of local datasets during the training of a global model without raw data sharing, there remain some privacy and security weaknesses, such as membership inference attacks [19], [20] and Byzantine attacks [7], [21].”
Wang, X., & Dai, M. (2025) · Cluster Computing · doi:10.1007/s10586-025-05160-z
“So et al. et al. [17] introduced the single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning.”
Robust clustering federated learning with trusted anchor clients
Zhang, M., Li, Y., Wei, F., Wang, B., & Zhang, Y. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104210 · Cited by 1
Trustworthy Federated Edge Learning via Blockchain
Zhou, Y., Fang, W., Shi, Y., & Letaief, K. B. (2025) · Wireless networks · doi:10.1007/978-3-031-96649-1_9
Desai, H. (2025) · Medical virology · doi:10.1007/978-981-96-8919-4_10
SCDFL: A Secure and Byzantine-Resilient Decentralized Federated Learning Framework
Fu, X., Chen, Y., Li, J., & Wang, X. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-0129-8_2
Wang, X., Li, S., Fan, F., Wang, S., Li, Y., & Zheng, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3543-9_22
Feng, L., Guo, J., Fang, F., He, Z., Yu, Y., Yao, S., & Peng, X. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3641964 · Cited by 2
Lightweight federated learning with dynamic anonymity
Sun, Z., Zhao, Q., & Zhao, G. (2025) · doi:10.1117/12.3092569
“So et al. 17 developed the BREA protocol, which integrated SS and the Krum algorithm to enhance privacy protection and Byzantine robustness, though the computational complexity of ciphertext aggregation remained high.”
Jahani, K., Moshiri, B., & Khalaj, B. H. (2025) · HAL · doi:10.22111/ieco.2025.51226.1668
Fed-Brmc: Byzantine-Robust Federated Learning Via Dual-Model Contrastive Detection
Gan, X., Lu, P., Gan, S., Xian, Y., Peng, K., Liu, P., & Li, D. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.11169733
“Email: liupeng@gxnu.edu.cn Byzantine attacks in FL, primarily based on clustering and statistical knowledge [5], [8], [20], [23], [24], are effective in independent and identically distributed (IID) settings but face limitations in non-independent and identically distributed (non-IID) settings.”
SDFL: a privacy-preserving Byzantine-robust decentralized federated learning scheme
Quan, H., Yanyi, Q. I. A. N., Hui, T. I. A. N., Xuefeng, L. I. U., Yue, L. I., Jianzong, W. A. N. G., & ZHONG, J. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0208
“为了覆盖所有可能的攻击场景 , 假设 4 个攻击者中有 2 个 为恶意客户端 , 他们在本地训练阶段对系统进行拜占庭攻击 , 具体为采用随机生成的高斯噪声替代本 地更新 [16,47] ; 另外 2 个为恶意委员会成员 , 他们在本地训练阶段表现为合法客户端 , 会提供正确的本 地更新 , 但在恶意客户端检测阶段或本地更新聚合阶段对系统进行攻击 , 具体为在恶意客户端检测阶 段随机构造错误的信任向量或在聚合阶段采用随机生成的高斯噪声替代 FVSS 份额 ; 在实验中 , 除了 恶意客户端 , 其他客户端随机均分 MNIST 和 FMNIST 的训练样本作为本地训练集 .”
On-demand Crowdsourced Federated Learning over Edge Devices
Tahir, M. (2025) · Dublin City University Open Access Institutional Repository (Dublin City University)
Xiao, D., Tang, J., & Chen, L. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11323165 · Cited by 1
Strategic Federated Learning: A Novel Game-Theoretic Approach to Secure and Efficient IoD
Sekhar, K. C., Varshini, D. V. D. S., Lakshmi, S. G. N. S., & Yogi, M. K. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-4277-1.ch007
Yousuf, M. J., Asghar, M. N., Ansari, M. S., Lee, B., & Kanwal, N. (2026) · doi:10.36227/techrxiv.176857882.23844900/v1
ByzTierFL: A Tiered Approach to Byzantine Robust and Decentralized Federated Learning
Xu, H., Dong, X., Wang, G., Peng, Z., Li, X., & Yu, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5719-6_42
Certifiably robust and privacy-preserving federated learning against backdoor attacks
Li, M., Ma, X., Teng, Z., Zhou, H., & Wei, L. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112063
FLET: Game-Theoretic Free-Riding Mitigation via Test Tasks in Federated Learning
Guo, S., Wang, Y., Su, Z., Pan, Y., Luan, T. H., & Luo, X. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3668944
“…Byzantine participants in FL, particularly free-riders, various defense schemes have been investigated, from the perspectives of outlier detection [9], [12], [13], [14] and contribution evaluation [7], [15], [16], [17]. i) Outlier detection identifies anomalous client updates using analytical or…”
Trustworthy Federated Learning With Authenticated ZKPs in Mobile Edge Intelligence
Li, Z., Chen, X., Sun, Q., Lu, Y., Li, D., Zhang, J., & Ai, B. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3670154
RAIN: Secure and Robust Aggregation under Shuffle Model of Differential PrivacyPreprint
Li, Y., Wang, Y., Tang, X., Jiang, P., Tan, Y., & Zhu, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.03108
“Following [45], the scaling attack is a targeted backdoor-style poisoning method.”
Federated Learning with Homomorphic Encryption for Secure Healthcare Applications
Gure, A. T., & Bochicchio, M. A. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402419
“Performance Benchmarks: FL for Healthcare and Challenges: Recent studies identify numerous challenges in implementing FL in healthcare, despite its great potential for enabling large-scale healthcare research while ensuring data privacy and security [29], [30].”
Attieh, H. A., Halilovic, M., Kerkouche, R., Rahimian, S., Wang, H., Rehms, R., Kaissis, G. A., Ziller, A., Kuntzer, J., Otte, K., et al. (2026) · IEEE Access · doi:10.1109/access.2026.3672991
A Malicious Client Defense Scheme in Federated Learning for Large‐Scale Edge Nodes
Guo, H., Chen, W., & Li, X. (2026) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70399
Privacy in Collaborative Deep Learning Systems: A Taxonomy and Archetypes
Rank, S., Jin, D. S., Thiebes, S., & Sunyaev, A. (2026) · ACM Computing Surveys · doi:10.1145/3801094
“Such CDL systems assume honest-but-curious data owners, whereas servers are assumed to be honest-but-curious or malicious [27, 84].”
Performance and Verifiability of IoT Security Protocols
Mansouri, M. (2023) · theses.fr (ABES) · doi:10.70675/c5a09e65z39ccz4810zb11bza7da4bf12251
QSFedMA: Quantum‐Secured Authentication Protocol for Privacy‐Preserving Federated IoMT
Goel, A., Nair, A., Chawla, D., Mehra, P. S., Rathore, R. S., & Jiang, W. (2026) · Software Practice and Experience · doi:10.1002/spe.70071
Adaptive client participation mechanism for federated learning in heterogeneous vehicular networks
Lin, W., & Zhou, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-48453-y
Sharma, T., & Sharma, B. (2026) · Intelligenza Artificiale · doi:10.1177/17248035261443435
“Byzantine-resilient aggregation (So et al., 2021) has become an important topic as FL moves into real-world networks.”
Parashar, A., & Mohan, M. (2026) · IEEE International Conference on Communication Systems and Network Technologies (CSNT) · doi:10.1109/csnt69054.2026.11502127
“To respond adversarial model updates, some methods including anti-poisoning and Byzantine-resilient aggregation have also been proposed [25][26].”
DDFL: dual defense against poisoning attacks in privacy-preserving federated learning
Guo, C., Tian, M., Li, X., Sun, H., & Jie, Y. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109095
Random Client Selection for Contrastive Federated Learning in Parameter Poisoning Attacks
Ginanjar, A., Li, X., Singh, P., & Hua, W. (2026) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi68585.2026.11539928
“Other defences, such as Byzantine [31] and other security enhancements [12] to the CFL, are not discussed in this study.”
Resource management for blockchain enhanced federated learning in wireless edge networks
Yang, Z., Weijing, Q., & Guo, L. (2026) · Scientific Reports · doi:10.1038/s41598-026-56310-1
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.