Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent
The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
We consider the distributed statistical learning problem over decentralized systems that are prone to adversarial attacks. This setup arises in many practical applications, including Google's Federated Learning. Formally, we focus on a decentralized system that consists of a parameter server and m working machines; each working machine keeps N/m data samples, where N is the total number of samples. In each iteration, up to q of the m working machines suffer Byzantine faults -- a faulty machine in the given iteration behaves arbitrarily badly against the system and has complete knowledge of the system. Additionally, the sets of faulty machines may be different across iterations. Our goal is to design robust algorithms such that the system can learn the underlying true parameter, which is of dimension d, despite the interruption of the Byzantine attacks. In this paper, based on the geometric median of means of the gradients, we propose a simple variant of the classical gradient descent method. We show that our method can tolerate q Byzantine failures up to 2(1+ε)q ≤ for an arbitrarily small but fixed constant ε > 0. The parameter estimate converges in O(log N) rounds with an estimation error on the order of max{√dq/N, √d/N, which is larger than the minimax-optimal error rate √d/N in the centralized and failure-free setting by at most a factor of √q. The total computational complexity of our algorithm is of O((Nd/m) log N) at each working machine and O(md + kd log3 N) at the cen…
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
“Apart from preserving privacy for individual users, edge AI also needs to be robust to errors and adversarial attackers, as the decentralized nature makes it easy to be unreliable in the learning process or even completely controlled by external attackers [74].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [74]
Citations
Cites
MapReduce: simplified data processing on large clusters
Dean, J., & Ghemawat, S. (2008) · Communications of the ACM · doi:10.1145/1327452.1327492 · Cited by 18,476 · cited 2×
“Many efficient distributed machine learning algorithms [6, 13] and system implementations [24, 28, 10, 19] have been proposed and studied.”
BackgroundBoyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
(1992) · Lecture Notes in Computer Science · doi:10.1007/bfb0022433 · Cited by 3,955
Privacy-preserving data mining
Agrawal, R., & Srikant, R. (2000) · ACM SIGMOD Record · doi:10.1145/335191.335438 · Cited by 2,961
Distributed GraphLab: a framework for machine learning and data mining in the cloud
Low, Y., Bickson, D., Gonzalez, J., Guestrin, C., Kyrola, A., & Hellerstein, J. M. (2012) · Proceedings of the VLDB Endowment · doi:10.14778/2212351.2212354 · Cited by 1,653 · cited 2×
“Many efficient distributed machine learning algorithms [6, 13] and system implementations [24, 28, 10, 19] have been proposed and studied.”
BackgroundNetwork Security: Private Communication in a Public World
Kaufman, C., Perlman, R., & Speciner, M. (1995) · Cited by 730
Geometric median and robust estimation in Banach spaces
Minsker, S. (2015) · Bernoulli · doi:10.3150/14-bej645 · Cited by 261
Agnostic Estimation of Mean and Covariance
Lai, K. A., Rao, A. B., & Vempala, S. (2016) · 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS) · doi:10.1109/focs.2016.76 · Cited by 204 · cited 1×
“A recent line of work [8, 15] presents polynomial algorithms to consistently estimate the mean and covariance of a distribution from N i.”
BackgroundRobust Estimators in High Dimensions without the Computational Intractability
Diakonikolas, I., Kamath, G., Kane, D. M., Li, J., Moitra, A., & Stewart, A. (2016) · 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS) · doi:10.1109/focs.2016.85 · Cited by 200 · cited 1×
“A recent line of work [8, 15] presents polynomial algorithms to consistently estimate the mean and covariance of a distribution from N i.”
BackgroundCommunication-efficient algorithms for statistical optimization
(2013) · Journal of Machine Learning Research · doi:10.5555/2567709.2567769 · Cited by 195 · cited 1×
“One-Shot Aggregation: On the other end of the spectrum, using a One-Short Aggregation method, each working machine computes an estimate of the model parameter using only its local data and reports it to the server, which then aggregates all the estimates reported to obtain a final estimate [33, 32].”
Method
Research works printed but not linked: 15
- Peva Blanchard , El Mahdi El Mhamdi , Rachid Guerraoui, and Julien Stainer. 2017 . Byzantine-Tolerant Machine Learning . arXiv preprint arXiv:1703.02757 (2017). Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, and Julien Stainer. 2017. Byzantine-Tolerant Machine Learning. arXiv preprint arXiv:1703.02757 (2017). · arXiv
- Stephen Boyd and Lieven Vandenberghe . 2004. Convex optimization . Cambridge university press . Stephen Boyd and Lieven Vandenberghe. 2004. Convex optimization. Cambridge university press.
- John Duchi Martin J Wainwright and Michael I Jordan. 2013. Local privacy and minimax bounds: Sharp rates for probability estimation. Advances in Neural Information Processing Systems. 1529--1537. John Duchi Martin J Wainwright and Michael I Jordan. 2013. Local privacy and minimax bounds: Sharp rates for probability estimation. Advances in Neural Information Processing Systems. 1529--1537.
- Jiashi Feng , Huan Xu , and Shie Mannor . 2014. Distributed Robust Learning. arXiv preprint arXiv:1409.5937 ( 2014 ). Jiashi Feng, Huan Xu, and Shie Mannor. 2014. Distributed Robust Learning. arXiv preprint arXiv:1409.5937 (2014). · arXiv
- Michael I Jordan , Jason D Lee , and Yun Yang . 2016. Communication-Efficient Distributed Statistical Inference. arXiv preprint arXiv:1605.07689 ( 2016 ). Michael I Jordan, Jason D Lee, and Yun Yang. 2016. Communication-Efficient Distributed Statistical Inference. arXiv preprint arXiv:1605.07689 (2016). · arXiv
- JHB Kemperman . 1987. The median of a finite measure on a Banach space. Statistical data analysis based on the L1-norm and related methods (Neuchâtel , 1987 ) (1987), 217--230. JHB Kemperman. 1987. The median of a finite measure on a Banach space. Statistical data analysis based on the L1-norm and related methods (Neuchâtel, 1987) (1987), 217--230.
- Jakub Konevcnỳ , Brendan McMahan , and Daniel Ramage . 2015. Federated optimization: Distributed optimization beyond the datacenter. arXiv preprint arXiv:1511.03575 ( 2015 ). Jakub Konevcnỳ, Brendan McMahan, and Daniel Ramage. 2015. Federated optimization: Distributed optimization beyond the datacenter. arXiv preprint arXiv:1511.03575 (2015). · arXiv
- Hendrik P Lopuhaa and Peter J Rousseeuw . 1991. Breakdown points of affine equivariant estimators of multivariate location and covariance matrices. The Annals of Statistics ( 1991 ), 229--248. Hendrik P Lopuhaa and Peter J Rousseeuw. 1991. Breakdown points of affine equivariant estimators of multivariate location and covariance matrices. The Annals of Statistics (1991), 229--248.
- Nancy A. Lynch . 1996. Distributed Algorithms . Morgan Kaufmann Publishers Inc ., San Francisco, CA, USA. \showISBNx9780080504704 Nancy A. Lynch. 1996. Distributed Algorithms. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA. \showISBNx9780080504704
- Song Mei , Yu Bai , and Andrea Montanari . 2016. The landscape of empirical risk for non-convex losses. arXiv preprint arXiv:1607.06534 ( 2016 ). Song Mei, Yu Bai, and Andrea Montanari. 2016. The landscape of empirical risk for non-convex losses. arXiv preprint arXiv:1607.06534 (2016). · arXiv
- Philipp Moritz , Robert Nishihara , Ion Stoica , and Michael I Jordan . 2015 . Sparknet: Training deep networks in spark. arXiv preprint arXiv:1511.06051 (2015). Philipp Moritz, Robert Nishihara, Ion Stoica, and Michael I Jordan. 2015. Sparknet: Training deep networks in spark. arXiv preprint arXiv:1511.06051 (2015). · arXiv
- Charles P. Pfleeger and Shari Lawrence Pfleeger . 2002 . Security in Computing (3rd ed.). Prentice Hall Professional Technical Reference . Charles P. Pfleeger and Shari Lawrence Pfleeger. 2002. Security in Computing (3rd ed.). Prentice Hall Professional Technical Reference.
- Foster J Provost and Daniel N Hennessy . 1996 . Scaling up: Distributed machine learning with cooperation . AAAI/IAAI , Vol. 1 . Citeseer, 74--79. Foster J Provost and Daniel N Hennessy. 1996. Scaling up: Distributed machine learning with cooperation. AAAI/IAAI, Vol. 1. Citeseer, 74--79.
- R. Vershynin . 2010. Introduction to the non-asymptotic analysis of random matrices. Arxiv preprint arxiv:1011.3027 ( 2010 ). R. Vershynin. 2010. Introduction to the non-asymptotic analysis of random matrices. Arxiv preprint arxiv:1011.3027 (2010). · arXiv
- 10.5555/1833515.1833620 · doi:10.5555/1833515.1833620
Cited by
Items 101–200 of 390
Privacy-Preserving and Poisoning-Defending Federated Learning in Fog Computing
Li, Y., Zhang, S., Chang, Y. Z., Xu, G., & Li, H. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3302795 · Cited by 23
Byzantines Can Also Learn From History: Fall of Centered Clipping in Federated Learning
Özfatura, K., Özfatura, E., Küpçü, A., & Gündüz, D. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3345171 · Cited by 26
Benchmarking robustness and privacy-preserving methods in federated learning
Alebouyeh, Z., & Bidgoly, A. J. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.01.009 · Cited by 21
Robust Distributed Optimization With Randomly Corrupted Gradients
Turan, B., Uribe, C. A., Wai, H.-T., & Alizadeh, M. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3185885 · Cited by 24
RFVIR: A robust federated algorithm defending against Byzantine attacks
Wang, Y., Zhai, D., & Xia, Y. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102251 · Cited by 21
Siren+: Robust Federated Learning With Proactive Alarming and Differential Privacy
Guo, H., Wang, H., Song, T., Yang, H., Ma, R., Jin, X., Xue, Z., & Guan, H. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3362534 · Cited by 27
Privacy-preserving federated learning compatible with robust aggregators
Alebouyeh, Z., & Bidgoly, A. J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110078 · Cited by 22
Secure Distributed Optimization Under Gradient Attacks
Yu, S., & Kar, S. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3277211 · Cited by 26
“In particular, in the special case when the graph G is complete, we may choose W = (1/n)11 which recovers computing in centralized scenarios, then the problem setup reduces to the Byzantine distributed optimization where a trusted central server is present and ρ-fraction working clients may report adversarial gradient…”
BackgroundMethodByzantine-resilient Distributed Large-scale Matrix Completion
Lin, F., Ling, Q. H., & Xiong, Z. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683121 · Cited by 19
Defenses Against Byzantine Attacks in Distributed Deep Neural Networks
Xia, Q., Tao, Z., & Li, Q. (2020) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2020.3035112 · Cited by 18
Byzantine-Resilient High-Dimensional Federated Learning
Data, D., & Diggavi, S. N. (2023) · IEEE Transactions on Information Theory · doi:10.1109/tit.2023.3284427 · Cited by 18
“Moreover, as opposed to [17], [20], and [22], our results are in a more general heterogeneous data model.”
BackgroundResultInfluentialBlades: A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning
Li, S., Ngai, E. C. ‐., Ye, F., Ju, L., Zhang, T., & Voigt, T. (2024) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi61053.2024.00018 · Cited by 28
Data Encoding for Byzantine-Resilient Distributed Gradient Descent
Data, D., Song, L., & Diggavi, S. N. (2018) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2018.8636017 · Cited by 21
Backdoor Federated Learning-Based mmWave Beam Selection
Zhang, Z.-M., Yang, R., Zhang, X., Li, C.-G., Huang, Y.-M., & Yang, L.-X. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3200111 · Cited by 12
Extremum Seeking Under Persistent Gradient Deception: A Switching Systems Approach
Galarza-Jimenez, F., Poveda, J. I., Bianchin, G., & Dall’Anese, E. (2021) · IEEE Control Systems Letters · doi:10.1109/lcsys.2021.3050451 · Cited by 15
Securing Federated Learning against Overwhelming Collusive Attackers
Ranjan, P., Gupta, A., Corò, F., & Das, S. K. (2022) · Globecom · doi:10.1109/globecom48099.2022.10000830 · Cited by 20
“Further, some researchers have focused on robust aggregation methods such as Krum and Multi-Krum [5], median and trimmed median [10], and GoeMed [11].”
MethodDetection and Mitigation of Label-Flipping Attacks in FL Systems With KL Divergence
Zang, L., & Li, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3424188 · Cited by 19
Byzantine fault tolerance in distributed machine learning: a survey
Bouhata, D., Moumen, H., Mazari, J. A., & Bounceur, A. (2024) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2024.2391778 · Cited by 30
He, Y., Zhang, J., Yang, P., Sun, Z., & Shen, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3602911 · Cited by 17
Incentive-Driven Long-term Optimization for Edge Learning by Hierarchical Reinforcement Mechanism
Liu, Y., Wu, L., Zhan, Y., Guo, S., & Hong, Z. (2021) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs51616.2021.00013 · Cited by 13
Generalization Error Matters in Decentralized Learning Under Byzantine Attacks
Ye, H., & Ling, Q. H. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3526989 · Cited by 12
Provably Robust Federated Reinforcement Learning
Fang, M., Wang, X., & Gong, N. Z. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714728 · Cited by 29
Gupta, N., Liu, S., & Vaidya, N. H. (2021) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w52860.2021.00037 · Cited by 20
Incentive mechanism for collaborative distributed learning in Artificial Intelligence of Things
Wang, G., Yin, J.-L., Hossain, M. S., & Muhammad, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.06.015 · Cited by 13
Towards Resilience for Multi-Agent QD-Learning
Xie, Y., Mou, S., & Sundaram, S. (2021) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc45484.2021.9683145 · Cited by 16
“Resilient algorithms against various types of attackers for networked systems have been proposed for different problems such as consensus [6]–[8], distributed optimization [5], [9], [10] and distributed learning [11]–[15].”
BackgroundFederated Learning Resilient to Byzantine Attacks and Data Heterogeneity
Zuo, S., Yan, X., Fan, R., Hu, H., Shan, H., Quek, T. Q. S., & Zhao, P. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3571058 · Cited by 24
Wajahat, A., Zhang, K., Latif, J., Ma, X., Ahad, A., & Ahmed, K. I. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70441 · Cited by 15
MITDBA: Mitigating Dynamic Backdoor Attacks in Federated Learning for IoT Applications
Wang, Y., Zhai, D., Han, D., Guan, Y., & Xia, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3325634 · Cited by 14
Cellular Traffic Prediction via Byzantine-Robust Asynchronous Federated Learning
Ma, H., Yang, K., & Jiao, Y. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3545912 · Cited by 22
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
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
Self-citationDistributed Byzantine Tolerant Stochastic Gradient Descent in the Era of Big Data
Jin, R., He, X., & Dai, H. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8761674 · Cited by 12
“As is shown in [6] and [7], even a single Byzantine worker can severely disrupt the convergence of distributed gradient descent algorithms.”
BackgroundMethodByzantine Fault-Tolerance in Federated Local SGD Under $2f$-Redundancy
Gupta, N., Doan, T. T., & Vaidya, N. H. (2023) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2023.3237489 · Cited by 22
Intrusion detection framework based on homomorphic encryption in AMI network
Wang, J., Xia, Z., Chen, Y., Hu, C., & Yu, F. (2022) · Frontiers in Physics · doi:10.3389/fphy.2022.1102892 · Cited by 12
“Chen et al. [19] used the gradient dimension median as a global update.”
MethodSelf-citationResilient Multiagent Reinforcement Learning With Function Approximation
Ye, L., Figura, M., Lin, Y., Pal, M., Das, P., Liu, J., & Gupta, V. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3409676 · Cited by 17
Robust Distributed Learning Against Both Distributional Shifts and Byzantine Attacks
Zhou, G., Xu, P., Wang, Y., & Tian, Z. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3436149 · Cited by 12
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
“Employing a similar fashion of model update, instead of using the average, [9] also proposes to use the median while [10], [11] use the geometric mean on the “clean” (i.”
MethodSu, L. (2020) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/3380908.3380916 · Cited by 12
Self-citationCommunication-Efficient and Resilient Distributed Q -Learning
Xie, Y., Mou, S., & Sundaram, S. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3292036 · Cited by 10
He, 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
Variance Reduction-Boosted Byzantine Robustness in Decentralized Stochastic Optimization
Peng, J., Li, W., & Ling, Q. H. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746340 · Cited by 11
Communication Efficient and Byzantine Tolerant Distributed Learning
Ghosh, A., Maity, R. K., Kadhe, S., Mazumdar, A., & Ramachandran, K. (2020) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit44484.2020.9174391 · Cited by 14
On Robustness of the Normalized Subgradient Method with Randomly Corrupted Subgradients
Turan, B., Uribe, C. A., Wai, H.-T., & Alizadeh, M. (2021) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc50511.2021.9483127 · Cited by 10
Median-Truncated Gradient Descent: A Robust and Scalable Nonconvex Approach for Signal Estimation
Chi, Y., Li, Y., Zhang, H., & Liang, Y. (2019) · Applied and numerical harmonic analysis · doi:10.1007/978-3-319-73074-5_8 · Cited by 11
“Very recently, geometric median is also adopted for robust empirical risk minimization [59, 60, 61].”
DP-Poison: Poisoning Federated Learning under the Cover of Differential Privacy
Zheng, H., Chen, J., Liu, T., Cheng, Y., Wang, Z., Wang, Y., Gao, L., Ji, S., & Zhang, X. (2024) · ACM Transactions on Privacy and Security · doi:10.1145/3702325 · Cited by 12
Byzantine-Robust and Communication-Efficient Personalized Federated Learning
Zhang, J., He, X., Huang, Y., & Ling, Q. H. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3514802 · Cited by 14
A defense method against multi-label poisoning attacks in federated learning
Ma, W., Zhao, Q., & Tian, W. (2025) · Scientific Reports · doi:10.1038/s41598-025-09672-x · Cited by 17
Design of Anti-Plagiarism Mechanisms in Decentralized Federated Learning
Shao, Y., Li, J., Ding, M., Wei, K., Ma, C., Shi, L. X., Chen, W., & Jin, S. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3376247 · Cited by 8
Voltran: Unlocking Trust and Confidentiality in Decentralized Federated Learning Aggregation
Wang, H. H., Cai, Y., Wang, J., Ma, C., Ge, C., Qu, X., & Zhou, L. Q. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3472531 · Cited by 9
Byzantine-Robust Federated Deep Deterministic Policy Gradient
Lin, Q., & Ling, Q. H. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746320 · Cited by 8
Federated Learning with Anomaly Client Detection and Decentralized Parameter Aggregation
Liu, S., & Shang, Y. (2022) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w54100.2022.00016 · Cited by 8
Blockchain-based Monitoring for Poison Attack Detection in Decentralized Federated Learning
Mallah, R. A., & Lopez, D. L. (2022) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme55909.2022.9988067 · Cited by 14
“Regarding the cybersecurity of FL and protection against this type of attack, many defenses were proposed for the centralized federated learning setting [1], [2], [3], [11].”
BackgroundByzantine-Robust Stochastic Gradient Descent for Distributed Low-Rank Matrix Completion
He, X., Ling, Q. H., & Chen, T. (2019) · IEEE Data Science Workshop (DSW) · doi:10.1109/dsw.2019.8755575 · Cited by 10
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
Dual-Domain Defenses for Byzantine-Resilient Decentralized Resource Allocation
Wang, R., Ling, Q. H., & Tian, Z. (2024) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2024.3485508 · Cited by 7
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
DualGuard: Obfuscated Federated Learning With Two-Party Secure Robust Aggregation
Pan, H., Bao, H., Guan, M., Li, Z., Huang, C., & Dai, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3533087 · Cited by 8
FedCmp: Byzantine-robust federated learning through clustering model update parameters
Wang, H., Wang, S., Wang, R., & Wang, P. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122377 · Cited by 7
Adapting Aggregation Rule for Robust Federated Learning under Dynamic Attacks
Hu, C., Zhang, M., Li, N., Li, J., Yang, Z., Hassan, M. U., & Tei, K. (2025) · International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) · doi:10.1109/seams66627.2025.00026 · Cited by 10
Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation
Wu, Z., Shen, H., Chen, T., & Ling, Q. H. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413992 · Cited by 8
“Algorithms in this regime replace the mean or weighted mean aggregation rules in Byzantine-free stochastic gradient methods with robust aggregation rules, such as geometric median [19], coordinate-wise median [20], trimmed mean [21], Krum [22], and RSA [23], or robustify the updates with malicious agent identification…”
MethodOnline Decentralized Multi-Agents Meta-Learning With Byzantine Resiliency
Odeyomi, O. T., Ude, B., & Roy, K. (2023) · IEEE Access · doi:10.1109/access.2023.3291677 · Cited by 7
Trading Communication for Computation in Byzantine-Resilient Gradient Coding
Hofmeister, C., Maßny, L., Yaakobi, E., & Bitar, R. (2023) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit54713.2023.10206794 · Cited by 7
Protecting Label Distribution in Cross-Silo Federated Learning
Jiang, Y.-F., Luo, X., Wu, Y., Xiao, X., & Ooi, B. C. (2024) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp54263.2024.00113 · Cited by 12
Byzantine-Robust and Communication-Efficient Distributed Non-Convex Learning Over Non-IID Data
He, X., Zhu, H., & Ling, Q. H. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747090 · Cited by 9
Byzantine Resilience With Reputation Scores
Regatti, J. R., Chen, H., & Gupta, A. (2022) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton49937.2022.9929385 · Cited by 10
Byzantine-Tolerant Distributed Coordinate Descent
Data, D., & Diggavi, S. N. (2019) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2019.8849217 · Cited by 7
“Distributed computing with Byzantine adversaries has a rich history since the work of [5], and has received recent attention in the context of large-scale distributed optimization and learning [3], [4], [6].”
BackgroundDefending Against Data and Model Backdoor Attacks in Federated Learning
Wang, H., Mu, X., Wang, D., Xu, Q., & Li, K. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3415628 · Cited by 9
Zhu, X., & Li, H. (2025) · Applied Sciences · doi:10.3390/app15105472 · Cited by 9
Zhang, J., Deng, C., & Lu, A.-Y. (2026) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2026.3683008 · Cited by 6
Privacy-Preserving Federated Learning Framework via Blockchain and Committee Mechanism
Shu, Z., Zhao, H., Xu, B., Xun, W., & Xu, B. (2023) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct59356.2023.10419785 · Cited by 7
“Authors in [8] proposed a variation of the gradient descent based on the geometric median of the gradient mean and experimentally presented the tolerant of Byzantine failure.”
BackgroundSun, H., Zhang, Y., Zhuang, H., Li, J., Xu, Z., & Wu, L. (2025) · The Computer Journal · doi:10.1093/comjnl/bxae086 · Cited by 11
FLock: Robust and Privacy-Preserving Federated Learning based on Practical Blockchain State Channels
Chen, R., Dong, Y., Liu, Y., Fan, T., Li, D., Guan, Z., Liu, J., & Zhou, J. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714666 · Cited by 14
Hu, J., Chen, G., Li, H., Guo, X., Ran, L., & Huang, T. (2025) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2025.3565568 · Cited by 6
On the Initial Behavior Monitoring Issues in Federated Learning
Mallah, R. A., Badu-Marfo, G., & Farooq, B. (2021) · IEEE Access · doi:10.1109/access.2021.3131102 · Cited by 6
Aspis: Robust Detection for Distributed Learning
Konstantinidis, K. T., & Ramamoorthy, A. (2022) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit50566.2022.9834813 · Cited by 6
“The first category of related prior work is called robust aggregation (Damaskinos et al., 2019; Yin et al., 2019; 2018; Xie et al., 2018; Blanchard et al., 2017; Chen et al., 2017).”
BackgroundDistributionally Robust Federated Learning for Differentially Private Data
Shi, S., Hu, C., Wang, D., Zhu, Y., & Han, Z. (2022) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs54860.2022.00086 · Cited by 10
“Representative examples include Trimmed mean [24] uses trimmed average value as the agregated model, and GeoMed [15] computes the geometric median of all local models to update the global model.”
MethodInfluentialSecuring Distributed Gradient Descent in High Dimensional Statistical Learning
Su, L., & Xu, J. (2019) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/3376930.3376983 · Cited by 7
Self-citationRobust and privacy-preserving collaborative training: a comprehensive survey
Yang, F., Zhang, X., Guo, S., Chen, D., Gan, Y., Xiang, T., & Liu, Y. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10797-0 · Cited by 23
Byzantine-Robust Federated Learning Framework via a Server-Client Defense Mechanisms
Song, A., Zhang, T., Cheng, K., Cao, Y., Zhu, X., & Shen, Y. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3568443 · Cited by 11
A Secure Dynamic Spectrum Access Scheme for Internet of Things With Swarm Learning
Li, F., Wang, Y., Lam, K., Shen, B., & Wang, L. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3583710 · Cited by 5
Reliable and Secure Anomaly Detection in Heterogeneous Federated Learning: A Comprehensive Review
Xiang, H., Wang, G., Yu, X., Di, F., Gao, R., Zhang, Y., & Han, X. (2026) · Big Data Mining and Analytics · doi:10.26599/bdma.2025.9020067 · Cited by 13
One-Bit Byzantine-Tolerant Distributed Learning via Over-the-Air Computation
Yang, Y., Wu, Y., Jiang, Y., & Shi, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3326438 · Cited by 6
FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders
Gu, H., Fan, L., Tang, X., & Yang, Q. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3375287 · Cited by 7
ToFi: An Algorithm to Defend Against Byzantine Attacks in Federated Learning
Xia, Q., Tao, Z., & Li, Q. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-90019-9_12 · Cited by 8
“From this figure, we can see that the performance of Krum is not as good as ToFi, GeoMedian, and FABA, while these three methods have very similar performance in the naive heterogeneous environment for these three different types of attacks.”
BackgroundMethodInfluentialLiu, Y., Guo, S., Zhan, Y., Wu, L., Hong, Z., & Zhou, Q. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3350654 · Cited by 6
Byzantine-Resilient Federated PCA and Low-Rank Column-Wise Sensing
Singh, A. P., & Vaswani, N. (2024) · IEEE Transactions on Information Theory · doi:10.1109/tit.2024.3442211 · Cited by 7
Yang, Y., Li, Q., Nie, C., Hong, Y., & Wang, B. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679566 · Cited by 10
Godavarthi, S., & Venkateswara Rao, G. (2024) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.538 · Cited by 7
A Review of Adversarial Behaviour in Distributed Multi-Agent Optimisation
Fanitabasi, F. (2018) · IEEE/ACM International Conference on Utility and Cloud Computing Companion (UCC Companion) · doi:10.1109/ucc-companion.2018.00034 · Cited by 6
Logarithmic Communication for Distributed Optimization in Multi-Agent Systems
London, P., Vardi, S., & Wierman, A. (2020) · ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS) · doi:10.1145/3393691.3394197 · Cited by 4
RAFL: A Robust and Adaptive Federated Meta-Learning Framework Against Adversaries
Yu, Z., Lu, Y., & Suri, N. (2023) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass58611.2023.00068 · Cited by 6
“These datasets have been widely used as benchmarks in FL [12] [14] [15].”
BackgroundMethodInfluentialLogarithmic Communication for Distributed Optimization in Multi-Agent Systems
London, P., Vardi, S., & Wierman, A. (2019) · Proceedings of the ACM on Measurement and Analysis of Computing Systems · doi:10.1145/3366696 · Cited by 6
“In the Byzantine faulty tolerance, some components of the distributed system are unreliable and perhaps adversarial [18].”
BackgroundDistributed Statistical Machine Learning in Adversarial Settings
Chen, Y., Su, L., & Xu, J. (2019) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/3308809.3308857 · Cited by 5
Self-citationHan, D., Liu, K., Xia, Y., & Xie, L. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3579218 · Cited by 4
A Byzantine-Resilient Dual Subgradient Method for Vertical Federated Learning
Yuan, K., Wu, Z., & Ling, Q. H. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747270 · Cited by 7
Privacy-Preserving Detection of Poisoning Attacks in Federated Learning
Muhr, T., & Zhang, W. (2022) · Conference on Privacy, Security and Trust · doi:10.1109/pst55820.2022.9851993 · Cited by 6
zkFL: Verifiable Byzantine-Robust Federated Learning Against Malicious Servers
Tang, X., Li, M., Zhang, T., Lin, Y., Zhu, L., Zhou, C., & Liu, X. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3622060 · Cited by 8
Robust Reward-Free Actor–Critic for Cooperative Multiagent Reinforcement Learning
Lin, Q., & Ling, Q. H. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3302131 · Cited by 7
Zhang, 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
FLEvaluate: Robust Federated Learning Based on Trust Evaluate
Guo, C., Guo, B., Zhu, T., Liu, P., & Cheng, G. (2023) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom60117.2023.00320 · Cited by 5
Metadata
- Authors
- Chen, Y., Su, L., & Xu, J.
- Affiliations
- Cornell University (US)
- University of Illinois Urbana-Champaign (US)
- Purdue University West Lafayette (US)
- Venue
- Proceedings of the ACM on Measurement and Analysis of Computing Systems
- Published
- 2017-12-19
- Volume
- 1
- Issue
- 2
- Pages
- 1-25
- ISSN
- 2476-1249 (ISSN-L)
- OpenAlex
- W4252654521
- Cited by
- 390
- References
- 15
- Citations by year
- 2026: 36 · 2025: 85 · 2024: 68 · 2023: 61 · 2022: 47 · 2021: 44 · 2020: 28 · 2019: 14 · 2018: 7
- FWCI
- 8.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Proceedings of the ACM on Measurement and Analysis of Computing Systems (publishedVersion)
- Funders
- NSF (CRII award 1657420; CCF-1704828; ECCS-1610543; CCF-0939370)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Keywords
- Byzantine faults, federated learning, decentralized systems, parameter server, linear regression, communication complexity
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.