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 101–200 of 316
Hao, J., Naja, R., & Zeghlache, D. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110456 · Cited by 17
DPAD: Data Poisoning Attack Defense Mechanism for federated learning-based system
Basak, S., & Chatterjee, K. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109893 · Cited by 20
BPS-FL: Blockchain-Based Privacy-Preserving and Secure Federated Learning
Yu, J., Yao, H., Ouyang, K., Cao, X., & Zhang, L. (2024) · Big Data Mining and Analytics · doi:10.26599/bdma.2024.9020053 · Cited by 17
Robust and Verifiable Privacy Federated Learning
Lu, Z. G., Lu, S., Tang, X., & Wu, J. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3309273 · Cited by 23
A Survey on Fault-tolerance in Distributed Optimization and Machine LearningPreprint
Liu, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.08545 · Cited by 20
“[94] proposed Byzantine-resilient secure aggregation (BREA) framework to achieve both privacy-preservation and fault-tolerance in federated learning.”
BackgroundLightSecAgg: Rethinking Secure Aggregation in Federated LearningPreprint
Yang, C.-S., So, J., He, C., Li, S., Yu, Q., & Avestimehr, S. (2021) · arXiv (Cornell University) · Cited by 23
Self-citationPan, Y., Su, Z., Wang, Y., Zhou, J., & Mahmoud, M. M. E. A. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3524834 · Cited by 17
PBFL: Privacy-Preserving and Byzantine-Robust Federated-Learning-Empowered Industry 4.0
Li, W., Fan, K., Yang, K., Yang, Y., & Li, H. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3315226 · Cited by 18
“Therefore, some works [13], [27], [28], [29] further ensure local data confidentiality with 2PC techniques.”
BackgroundYou, J., Yang, R., Zhan, Y., Song, B., Zhang, Y., & Wang, Z. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3550635 · Cited by 15
“Current strategies for boosting Byzantine resilience often rely on filtering client updates, typically by removing outliers [31] or selecting median values [32] to achieve a balanced parameterization of the model.”
Accelerating Federated Learning with genetic algorithm enhancements
Zheng, H., Chu, J., Li, Z., Ji, J., & Li, T. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127636 · Cited by 15
Cluster-Based Secure Aggregation for Federated Learning
Kim, J., Park, G., Kim, M., & Park, S. (2023) · Electronics · doi:10.3390/electronics12040870 · Cited by 15
“So et al. [24] proposed a distance-based outlier detection approach for single-server federated learning, which can calculate the pairwise distance between local updates by sharing the masked updates and pairwise distances between the masked shares.”
BackgroundMethodInfluentialMa, H., Li, Q., Zheng, Y., Zhang, Z., Liu, X., Gao, Y., Al-Sarawi, S. F., & Abbott, D. (2023) · Computers & Security · doi:10.1016/j.cose.2023.103406 · Cited by 16
Secure Aggregation for Clustered Federated Learning
Sami, H. U., & Güler, B. (2023) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit54713.2023.10206964 · Cited by 17
“We refer to [7], [29], [30] for the details of this conversion.”
BackgroundSCALR: Communication-Efficient Secure Multi-Party Logistic Regression
Lu, X., Sami, H. U., & Güler, B. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3308954 · Cited by 15
“For space considerations, we refer to [2], [4], [5], and [3] for the details of this mapping.”
BackgroundMethodResultInfluentialPandey, S., Singh, O., Pandey, A., & Pandey, C. (2025) · IEEE Access · doi:10.1109/access.2025.3596627 · Cited by 16
“Subsequent works introduced median based [18], [19] or trimmed mean [20] aggregators.”
Auditable Federated Learning With Byzantine Robustness
Liang, Y., Li, Y., & Shin, B. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2023.3266019 · Cited by 16
“The FL work [13] considers Byzantine clients with privacy preservation but assumes that the aggregator does not collude with clients.”
Proof-of-Contribution-Based Design for Collaborative Machine Learning on Blockchain
Buyukates, B., He, C., Han, S., Fang, Z., Zhang, Y., Long, J., Farahanchi, A., & Avestimehr, S. (2023) · IEEE International Conference on Decentralized Applications and Infrastructures (DAPPS) · doi:10.1109/dapps57946.2023.00012 · Cited by 14
Lu, S., Li, R., & Liu, W. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-023-2283-x · Cited by 17
Over-the-Air Federated Edge Learning With Hierarchical Clustering
Aygün, O., Kazemi, M., Gündüz, D., & Duman, T. M. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3457591 · Cited by 19
“Even though FL aims to protect the local data privacy, some studies show that it is possible to infer user data even from the gradient information, and present approaches to enhance data privacy [7], [13], [14].”
BackgroundRobust Aggregation for Federated Learning by Minimum γ-Divergence Estimation
Li, C.-J., Huang, P.-H., Ma, Y.-T., Hung, H., & Huang, S. (2022) · Entropy · doi:10.3390/e24050686 · Cited by 12
“In this article, we consider the case that there is a central server, which works as a coordinator and aggregates the gradient information sent by the local clients to update the global model through an iterative process [2].”
Mohamed, H., Koroniotis, N., Moustafa, N., Schiliro, F., & Zomaya, A. Y. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3492919 · Cited by 14
“8 attempts to inject malicious participants provide misleading updates during the model aggregation process causing convergence issues [111].”
Ullah, I., Deng, X., Pei, X., Mushtaq, H., Uzair, M., & Qayyum, S. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111705 · Cited by 13
FLARE: Defending Federated Learning Against Model Poisoning Attacks via Latent Space Representations
Wang, N., Zhang, C., Xiao, Y., Chen, Y., Lou, W., & Hou, Y. T. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3521297 · Cited by 16
“Despite many salient features of FL and its tremendous success in many applications, it has been shown recently that FL is vulnerable to model poisoning attacks (MPAs) [7], [8], [9], [10], [11].”
Kaheni, M., Usai, E., & Franceschelli, M. (2022) · IEEE Control Systems Letters · doi:10.1109/lcsys.2022.3173495 · Cited by 12
Auxo: Efficient Federated Learning via Scalable Client Clustering
Liu, J., Lai, F., Dai, Y., Akella, A., Madhyastha, H. V., & Chowdhury, M. (2023) · ACM Symposium on Cloud Computing (SoCC) · doi:10.1145/3620678.3624651 · Cited by 19
Blockchain Based Secure Federated Learning With Local Differential Privacy and Incentivization
Chaudhury, S. D., Morreddigari, L. R., Varun, M., Sengupta, T., Chakraborty, S., Sural, S., Vaidya, J. S., & Atluri, V. (2024) · IEEE Transactions on Privacy · doi:10.1109/tp.2024.3487819 · Cited by 12
“However, the standard implementations of FL are susceptible to various kinds of security and privacy attacks, such as data [4] and model poisoning [5], [6], interference [7] and Byzantine attacks [8], model extraction attacks [9], evasion attacks [10], etc.”
susFL: Federated Learning-based Monitoring for Sustainable, Attack-Resistant Smart Farms
Chen, D., Yang, P., Ha, D. S., & Cho, J.-H. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825116 · Cited by 11
Mintoo, A. A., Saimon, A. S. M., Bakhsh, M. M., & Akter, M. (2022) · American Journal of Scholarly Research and Innovation · doi:10.63125/sdz8km60 · Cited by 30
Rezaie, H., Taheri, R., Nowroozi, E., Hajizadeh, M., Shiaeles, S. N., & Bauschert, T. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3644477 · Cited by 17
“However, empirical evaluations under realistic non-IID data distributions, where clients hold skewed or heterogeneous data, have shown that these defenses are less effective [94], [95], [96].”
FedSuper: A Byzantine-Robust Federated Learning Under Supervision
Zhao, P., Jiang, J., & Zhang, G. (2023) · ACM Transactions on Sensor Networks · doi:10.1145/3630099 · Cited by 13
“The third category of defenses [33, 38, 51], [26, 29, 50] took the non-IID data into consideration, but they focused on the scenario that only a minority of worker devices are compromised.”
BackgroundMethodResultInfluentialHe, Y., Li, P., Ni, J., Deng, X., Lu, H., Zhang, J., & Yang, L. T. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3341637 · Cited by 11
The More, the Better: A Study on Collaborative Machine Learning for DGA Detection
Drichel, A., Holmes, B., von Brandt, J., & Meyer, U. (2021) · CYSARM@CCS · doi:10.1145/3474374.3486915 · Cited by 13
“[49] additionally present an integration of their de-”
BackgroundEARVP: Efficient Aggregation for Federated Learning With Robustness, Verifiability, and Privacy
Yan, C., Lu, X., Lió, P., & Hui, P. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3576008 · Cited by 12
“BREA [29] filters malicious gradients by calculating pairwise distances between updates and enhances privacy through verifiable outlier detection.”
Computationally Efficient Auto-Weighted Aggregation for Heterogeneous Federated Learning
Talukder, Z., & Islam, M. A. (2022) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge55608.2022.00015 · Cited by 11
“To defend against corrupted clients, various algorithms have been proposed in the literature for attaining robust federated learning [11], [20], [25].”
BackgroundMethodByzantine-Resilient Online Federated Learning with Applications to Network Traffic Classification
Wen, D., Li, Y., & Lau, F. C. M. (2023) · IEEE Network · doi:10.1109/mnet.014.2300054 · Cited by 15
RRFL: A rational and reliable federated learning incentive framework for mobile crowdsensing
He, Q., Tian, Y., Wang, S., & Xiong, J. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.101977 · Cited by 10
“Among the defense approaches, Krum is regarded as one of the most intriguing works against malicious users in FL and Euclidean distance is widely employed in robust aggregation schemes as a result.”
PlugVFL: Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Parties
Sun, J., Du, Z., Dai, A., Baghersalimi, S., Amirshahi, A., Atienza, D., & Chen, Y. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825534 · Cited by 10
“…from gradients (DLG) [48, 47], model inversion [8] and their variants [12, 18, 45, 29, 17], and model IP leakage, such as model extraction attacks [39, 32, 34, 7, 40], where multiple defensive methods have also been proposed to tackle data IP leakage [36, 30, 1, 3] and model IP leakage [19, 33].”
Low Complexity Byzantine-Resilient Federated Learning
Gouissem, A., Hassanein, S., Abualsaud, K., Yaacoub, E. E., Mabrok, M. A., Abdallah, M. M., Khattab, T. M., & Guizani, M. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3482727 · Cited by 10
“In [15], key sharing and node selection approaches are used to secure transmitted models.”
FedSSuper: A Secure and Private Federated Learning Under Trusted Supervision
Zhao, P., Jiang, J., & Zhang, G. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3572493 · Cited by 10
Clustered Graph Federated Personalized Learning
Gauthier, F., Gogineni, V. C., Werner, S., Huang, Y.-F., & Kuh, A. (2022) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf56349.2022.10051979 · Cited by 9
“Several studies have examined certain practical implementation challenges associated with federated learning, including communication efficiency [3], [4], privacy [5], asynchronous behavior [6], noisy communication links [7], and byzantine attacks [8].”
BackgroundWei, Z., Wang, J., Zhao, Z., & Zhao, Z. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103345 · Cited by 9
Secure Gradient Aggregation With Sparsification for Resource-Limited Federated Learning
Sami, H. U., & Güler, B. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3403475 · Cited by 11
“The local update x ti ( ℓ ) of each user i is converted to the finite field as follows, where f ( · ) is a stochastic rounding function [34], f ( x ) ≜ ⌊ qx ⌋ mod p probability 1 − ( qx − ⌊ qx ⌋ ) ⌊ qx ⌋ + 1 mod p otherwise such that q is a tuning parameter that quantifies the rounding loss.”
Byzantine-Resilient Federated Learning via Distributed Optimization
Xia, Y., Yu, W., & Li, Q. (2025) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226343 · Cited by 8
Byzantine-Resilient Federated Learning With Differential Privacy Using Online Mirror Descent
Odeyomi, O. T., & Zaruba, G. V. (2023) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/icnc57223.2023.10074494 · Cited by 8
Byzantine-Resilient Secure Federated Learning on Low-Bandwidth Networks
Masuda, H., Kita, K., Koizumi, Y., Takemasa, J., & Hasegawa, T. (2023) · IEEE Access · doi:10.1109/access.2023.3277858 · Cited by 11
“The paper chooses BREA [27], which is a Shamir’s secret sharing masking method, due to its stronger resilience than additive secret sharing masking methods (the reason is described later in Section V).”
BackgroundInfluentialFlag: A Framework for Lightweight Robust Secure Aggregation
Bangalore, L., Sereshgi, M. H. F., Hazay, C., & Venkitasubramaniam, M. (2023) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3579856.3595805 · Cited by 12
KVSAgg: Secure Aggregation of Distributed Key-Value Sets
Wu, Y., Dong, S., Zhou, Y., Zhao, Y., Fu, F., Yang, T., Niu, C., Wu, F., & Cui, B. (2023) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde55515.2023.00139 · Cited by 8
“However, secure aggregation is still required in FL because gradient vectors can leak user privacy and incur attacks [17]–[24].”
BackgroundXi, Y., Li, Q., & Mao, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128667 · Cited by 7
Cost-Efficient and Secure Federated Learning for Edge Computing
Zhang, Z., Wu, L., Wang, Z., Hu, J., Ma, C., & Liu, Q. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3590799 · Cited by 11
Detection and Mitigation of Byzantine Attacks in Distributed Training
Konstantinidis, K., Vaswani, N., & Ramamoorthy, A. (2023) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2023.3324697 · Cited by 7
“Robust aggregation methods have also been proposed for federated learning [27], [28]; however, as we make no assumption of privacy, our work, as well as the methods we compare with do not apply to federated learning.”
MethodSecure Aggregation for Clustered Federated Learning With Passive Adversaries
Sami, H. U., & Güler, B. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3366394 · Cited by 7
“Future directions include extending our mechanisms to active (malicious) adversaries who can modify the messages or datasets adversarially [42], and integrating our frameworks with authenticated key agreement mechanisms to ensure the integrity and authenticity of the messages exchanged against…”
BackgroundInfluentialTowards Practical Homomorphic Aggregation in Byzantine-Resilient Distributed Learning
Choffrut, A., Guerraoui, R., Pinot, R., Sirdey, R., Stephan, J., & Zuber, M. (2024) · International Middleware Conference · doi:10.1145/3652892.3700783 · Cited by 10
“Other works [22, 32, 33, 39, 51, 58, 63, 68, 76] make use of secure MPC to protect the privacy of the nodes.”
PRFL: Achieving Efficient Robust Aggregation in Privacy-Preserving Federated Learning
Liu, X., Yang, J., Chen, S., He, H., & Jiang, X. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3514212 · Cited by 7
“We test the model accuracy of PRFL when the proportion of malicious users is 0%, 5%, 10%, 15%, and 20%, and compare it with classical and recent aggregation rules such as Multi-Krum [31], RFA [21], LSFL [25] and ACORN-robust [36].”
InfluentialKianpisheh, S., Benzaïd, C., & Taleb, T. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901544 · Cited by 7
“The authors of [7] make FL robust against Byzantine clients while preserving the privacy of individual users.”
Probabilistic Byzantine Attack on Federated Learning
Wang, T.-H., Chen, P., & Huang, Y.-C. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3564842 · Cited by 6
“Byzantine attacks often occur in FL systems, as studied in works like [29] and [30], where the resilience of FL models to such attacks is thoroughly investigated.”
Wang, S., Tian, Y., Xiong, J., Ma, J., & Zhang, Y. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2025.3587771 · Cited by 9
“BREA [43], as a representative solution for Byzantine-robust verifiable aggregation, achieves robust aggregation without disclosing gradient information by comparing gradient shares.”
Ahmad, M., Habib, S., & Tariq, F. (2025) · VFAST Transactions on Software Engineering · doi:10.21015/vtse.v13i2.2163 · Cited by 6
A Privacy Robust Aggregation Method Based on Federated Learning in the IoT
Li, Q., Wang, X., & Ren, S. (2023) · Electronics · doi:10.3390/electronics12132951 · Cited by 7
Drowsiness Detection Using Federated Learning: Lessons Learnt from Dealing with Non-IID Data
Dautov, R., & Husom, E. J. (2024) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3652037.3652074 · Cited by 7
“In addition to these core metrics, studies have also examined FL’s performance in terms of fault tolerance and resilience [10, 31], energy efficiency [30, 41], model convergence speed [5, 13, 25], and algorithmic fairness [21, 43]. albeit beyond the scope of this paper, considering all these…”
BackgroundAbdulqadder, I. H., Aziz, I. T., & Zou, D. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110841 · Cited by 8
Godavarthi, S., & Venkateswara Rao, G. (2024) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.538 · Cited by 7
“This highlights the need for innovative solutions that balance security with practicality in diverse federated learning environments [19].”
BackgroundTIMPANY—deTectIon of Model Poisoning Attacks usiNg accuracY
Sameen, M., & Hwang, S. O. (2021) · IEEE Access · doi:10.1109/access.2021.3118926 · Cited by 6
Asynchronous Robust Aggregation Method with Privacy Protection for IoV Federated Learning
Zhou, A., Jiang, N., & Tang, T. (2024) · World Electric Vehicle Journal · doi:10.3390/wevj15010018 · Cited by 5
PraaKrum: A Practical Byzantine-Resilient Federated Learning Algorithm
Kukreja, P., & Mahendran, V. (2024) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets59351.2024.10427404 · Cited by 7
“In recent times, several works [8], [9], and [10] have adapted and extended Krum algorithm.”
BackgroundMethodInfluentialZhang, R., Hussain, S., Chen, H., Javaheripi, M., & Koushanfar, F. (2023) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3616868 · Cited by 7
Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning.Preprint
Tang, T., Ali, R. E., Hashemi, H., Gangwani, T., Avestimehr, S., & Annavaram, M. (2021) · arXiv (Cornell University) · Cited by 5
Duan, Q., Huang, J. G., Hu, S., Deng, R., Lu, Z., & Yu, S. (2022) · doi:10.36227/techrxiv.21788450 · Cited by 6
Pappas, C., Papadopoulos, D., & Papamanthou, C. (2025) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp61157.2025.00204 · Cited by 4
“There exist several works constructing secure (privacy-preserving) FL with robust aggregation (e.g., [98, 99, 100, 101, 102, 103, 104]), e.g., based on secure multi-party computation (MPC), secret-sharing, or homomorphic encryption.”
A Reputation-Aware Defense Framework for Strategic Behaviors in Federated Learning
Cai, Y., Xu, J., Lian, Z., Brian, K. C. W., Li, Y., & Xu, J. (2025) · Telecom · doi:10.3390/telecom6030060 · Cited by 6
Du, M., Zhang, M., Liu, L., Xu, K., & Yin, Q. (2023) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3605573.3605592 · Cited by 5
“2 Robustness for Federated Learning Aiming at alleviating the perturbation effect by Byzantine workers and strengthening the robustness of the machine learning system, numerous Byzantine-resilient federated learning algorithms were proposed[19][28][31].”
BackgroundScalable Multi-Round Multi-Party Privacy-Preserving Neural Network Training
Lu, X., Basaran, U. Y., & Güler, B. (2024) · IEEE Transactions on Information Theory · doi:10.1109/tit.2024.3441509 · Cited by 5
“A promising direction for future research is extending our frameworks for the latter, by leveraging Byzantine-resilient and verifiable secure multi-party computing mechanisms [63].”
BackgroundZhu, J., Tang, H., Li, S., & Chang, Y. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3492071 · Cited by 4
“We experimentally demonstrate the performance gain of GLCC in speeding up the training process in the presence of stragglers.”
Rokvic, L., Danassis, P., Karimireddy, S. P., & Faltings, B. V. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825097 · Cited by 7
“We do not consider threat scenarios as described in [7] and [52], where participants carefully craft malicious updates.”
Li, X., Tao, X., Chen, G., You, L., & Sun, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3573910 · Cited by 4
“In addition, a Multi-Krum-based framework, named as BREA [26], is proposed to enhance the privacy-preserving learning process under a quantized stochastic gradient setting.”
Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats
Zhang, C., Jin, H., Shi, S., Yu, H., Johns, S., Hou, Y. T., & Lou, W. (2025) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom64451.2025.11310549 · Cited by 8
Federated learning with bilateral defense via blockchain
Xiao, J., Nie, H., Yi, Z., Tang, X., & Lu, S. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107199 · Cited by 6
Venčkauskas, A., Toldinas, J., Morkevičius, N., Serkovas, E., & Krištaponis, M. (2025) · Electronics · doi:10.3390/electronics14061215 · Cited by 5
“The first single server solution for Byzantine-resilient secure federated learning and framework was proposed in [15].”
Cross the Chasm: Scalable Privacy-Preserving Federated Learning against Poisoning Attack
Li, Y., Hu, G., Liu, X., & Ying, Z. (2021) · Conference on Privacy, Security and Trust · doi:10.1109/pst52912.2021.9647750 · Cited by 7
Efficient federated learning under non-IID conditions with attackers
Zou, H., Zhang, Y., Que, X.-R., Liang, Y., & Crowcroft, J. (2022) · FedEdge@MobiCom · doi:10.1145/3556557.3557951 · Cited by 5
“Besides, BREA [19] alleviates this problem by a secure aggregation function.”
BackgroundSikandar, H. S., Malik, S. U. R., Anjum, A., Khan, A., & Jeon, G. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.07.037 · Cited by 5
FedQV: Leveraging Quadratic Voting in Federated Learning
Chu, T., & Laoutaris, N. (2024) · Proceedings of the ACM on Measurement and Analysis of Computing Systems · doi:10.1145/3656006 · Cited by 6
“Although a few FL aggregation approaches [35, 37, 51] can be adapted to incorporate secure aggregation, they still rely on majority voting as the aggregation scheme, which can be integrated with FedQV to enhance its robustness against poisoning attack. where 𝑟 𝑡 − 1 is the learning rate.”
On Attacks To Federated Learning and a Blockchain-empowered Protection
Esposito, C., Sperlí, G., Moscato, V., & Zhao, Z. (2022) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc49033.2022.9700723 · Cited by 4
On the Strategyproofness of the Geometric MedianPreprint
El-Mhamdi, E.-M., Farhadkhani, S., Guerraoui, R., & Hoang, L. N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02394 · Cited by 6
“…the geometric median to ensure safe learning despite the presence of participants with arbitrarily malicious behavior (Farhad-khani et al., 2022a; Karimireddy et al., 2022; Acharya et al., 2022; Wu et al., 2020; So et al., 2021; Gu and Yang, 2021; Pillutla et al., 2022; Farhadkhani et al., 2022b).”
Combining Differential Privacy and Byzantine Resilience in Distributed SGDPreprint
Guerraoui, R., Gupta, N., Pinot, R., Rouault, S., & Stephan, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03991 · Cited by 6
Fed-Trace: An Efficient Model to Traceback Data Poisoning Attacks in Federated Learning
Gupta, H. K., Pareek, P., Arora, A., Maini, M. D. K., Bhukya, R. K., Vyas, O. P., & Puliafito, A. (2023) · IEEE International Carnahan Conference on Security Technology (ICCST) · doi:10.1109/iccst59048.2023.10474250 · Cited by 3
“Byzantine-robust aggregation [25] uses methods like signed gradient updates and filtering to further defend against actively hostile clients.”
MethodA Privacy Preserving and Byzantine Robust Collaborative Federated Learning Method Design
Yang, N., Wang, S., Chen, M., Yin, C., & Brinton, C. G. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10622626 · Cited by 4
“The authors in [11], [12] have explored solutions for both privacy leakage and Byzantine attacks.”
BackgroundXue, K., Li, J., Xue, R., Xue, Y., & Zhao, J. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3632902 · Cited by 3
Practical Framework for Privacy-Preserving and Byzantine-Robust Federated Learning
Zhang, B., Fang, M., Liu, Z., Yi, B., Zhou, P., Wang, Y., Li, T., & Liu, Z. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3642546 · Cited by 6
“Few studies [14], [24], [27], [28], [66] address both Byzantine resilience and client data privacy simultaneously.”
InfluentialFRIDA: Free-rider detection using privacy attacks
Recasens, P. G., Horváth, Á., Gutierrez-Torre, A., Torres, J., Berral, J. L., & Pejó, B. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104357 · Cited by 7
Cai, Z., Chen, H., Zhu, G., Shi, Q., & Huang, K. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3677600 · Cited by 5
Technical considerations of federated learning in digital healthcare systems
Alozie, E., Olagunju, H. I., Faruk, N., & Garba, S. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13897-3.00009-6 · Cited by 5
MANDERA: Malicious node detection in federated learning via ranking
Zhu, W., Zhao, B. Z. H., Luo, S., & Deng, K. (2026) · The Annals of Applied Statistics · doi:10.1214/26-aoas2147 · Cited by 4
“…rely on the gradient values to determine whether a node is malicious or not, for example, (Blanchard et al., 2017; Yin et al., 2018; Guerraoui et al., 2018; Li et al., 2020; Fang et al., 2020; Cao et al., 2020; Wu et al., 2020b; Xie et al., 2019; 2020; Cao et al., 2021) and (So et al., 2021).”
Data Leakage in Federated Learning
Jin, X. P., Chen, P., & Chen, T. (2022) · Springer eBooks · doi:10.1007/978-3-030-96896-0_15 · Cited by 3
An Efficient Multi-Party Secure Aggregation Method Based on Multi-Homomorphic Attributes
Gao, Q., Sun, Y., Chen, X., Yang, F., & Wang, Y. (2024) · Electronics · doi:10.3390/electronics13040671 · Cited by 5
Mitigating Data Injection Attacks on Federated Learning
Shalom, O. O., Leshem, A., & Bajwa, W. U. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446615 · Cited by 3
“Even though the federated learning model preserves privacy, it is vulnerable to various security threats, including data injection and”
BackgroundByzantine Robust Federated Learning Scheme Based on Backdoor Triggers
Yang, Z., Gu, K., & Zuo, Y. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.050025 · Cited by 3
Rank-Two Correction and Fine-Tuning for Adaptive Byzantine Recovery in Federated Learning
Wang, X., & Yang, T. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3467275 · Cited by 3
DearFSAC: A DRL-based Robust Design for Power Demand Forecasting in Federated Smart Grid
Huang, C., Chen, W., Wang, X., Hong, F., Yang, S., Chen, Y., Bu, S., Jiang, C., Zhou, Y., & Zhang, Y. (2022) · Globecom · doi:10.1109/globecom48099.2022.10001127 · Cited by 3
“Briefly, in this paper, all conditions that cause model degradation are called defects, such as malicious updates (insider) by utility companies [4, 5], poisoning attacks (outsider) by hackers [4, 6], and low-quality data caused by communication lost or equipment failure.”
BackgroundDuan, Q., Huang, J. G., Hu, S., Deng, R., Lu, Z., & Yu, S. (2022) · doi:10.36227/techrxiv.21788450.v1 · Cited by 4
SABLE: Secure And Byzantine robust LEarningPreprint
Choffrut, A., Guerraoui, R., Pinot, R., Sirdey, R., Stephan, J., & Zuber, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.05395 · Cited by 6
“In this section, we present a comprehensive table of notations employed throughout the paper for clarity and reference.”
Method
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.