Robust Aggregation for Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning is the centralized training of statistical models from decentralized data on mobile devices while preserving the privacy of each device. We present a robust aggregation approach to make federated learning robust to settings when a fraction of the devices may be sending corrupted updates to the server. The approach relies on a robust aggregation oracle based on the geometric median, which returns a robust aggregate using a constant number of iterations of a regular non-robust averaging oracle. The robust aggregation oracle is privacy-preserving, similar to the non-robust secure average oracle it builds upon. We establish its convergence for least squares estimation of additive models. We provide experimental results with linear models and deep networks for three tasks in computer vision and natural language processing. The robust aggregation approach is agnostic to the level of corruption; it outperforms the classical aggregation approach in terms of robustness when the level of corruption is high, while being competitive in the regime of low corruption. Two variants, a faster one with one-step robust aggregation and another one with on-device personalization, round off the paper.
Key facts. Cited by 314 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Dec 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 32; 2022: 47; 2023: 61; 2024: 64; 2025: 68; 2026: 42.
314 papers.
Sort:
By area:
- 2021A Field Guide to Federated Optimizationcited by 312
- 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 124
- 2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 123
- 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
- 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
- 2021Federated Quantum Machine Learningcited by 82
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
- 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
- 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 64
- 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
- 2021EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learningcited by 53
38 more
- 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
- 2022A Survey on Heterogeneous Federated Learningcited by 42
- 2022Cross-Silo Federated Learning: Challenges and Opportunitiescited by 38
- 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
- 2021FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspectivecited by 35
- 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
- 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
- 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
- 2022Byzantine-Robust Decentralized Learning via ClippedGossipcited by 29
- 2023Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learningcited by 29
- 2023Integration of Large Language Models and Federated Learningcited by 28
- 2023Label Poisoning is All You Needcited by 27
- 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneitycited by 25
- 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
- 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
- 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
- 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
- 2021Robust Training in High Dimensions via Block Coordinate Geometric Median Descentcited by 20
- 2021Information Theoretic Secure Aggregation with User Dropoutscited by 19
- 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
- 2023Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Surveycited by 18
- 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 18
- 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
- 2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
- 2023A Huber Loss Minimization Approach to Byzantine Robust Federated Learningcited by 16
- 2021Learning-to-learn non-convex piecewise-Lipschitz functionscited by 15
- 2021SGDE: Secure Generative Data Exchange for Cross-Silo Federated Learningcited by 15
- 2022More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networkscited by 15
- 2022Few-shot Backdoor Attacks via Neural Tangent Kernelscited by 15
- 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
- 2021Federated Learning from Small Datasetscited by 14
- 2023Fusion of Global and Local Knowledge for Personalized Federated Learningcited by 14
- 2023Fedstellar: A Platform for Decentralized Federated Learningcited by 14
- 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 14
- 2021Faithful Edge Federated Learning: Scalability and Privacycited by 13
- 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splittingcited by 13
- 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updatescited by 13
- 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 13
50 most cited of 314 All 314 (JSON)
- 2026Robustifying Asynchronous SGD via Soft Throttling30 Sep 2026
- 2026Median Temporal Ensembling: Training-Free Robust Aggregation for Action-Chunked Visuomotor Policies22 Sep 2026
- 2026FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks22 Sep 2026
- 2026On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression22 Sep 2026
- 2026Structural Negative Transfer in Federated Graph Neural Networks: Diagnosis, Causal Investigation, and the Limits of Divergence-Aware Mitigation15 Sep 2026
- 2026Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface3 Sep 2026
- 2026Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning25 Aug 2026
- 2026STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation14 Aug 2026
- 2026Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning12 Aug 2026
- 2026Analysis of Federated Aggregation under Model Poisoning and Backdoor Attacks: A Reconstructed Cross-Dataset and Cross-Architecture Benchmark11 Aug 2026
- 2026FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks7 Aug 2026
- 2026Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning6 Aug 2026
38 more
- 2026Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning29 Jul 2026
- 2026Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries23 Jul 2026
- 2026Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Data13 Jul 2026
- 2026Secure Decentralized Federated Learning via Gossip and Virtual Voting9 Jul 2026
- 2026Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning3 Jul 2026
- 2026Privacy-Preserving and Verifiable Approximate Distributed Coded Computing2 Jul 2026
- 2026Federated Learning with Energy-Based Structured Probabilistic Inference29 Jun 2026
- 2026When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration27 Jun 2026
- 2026Model Multiplicity for Adversarial Detection in Small Language Model Training on Edge Devices5 Jun 2026
- 2026Practical Validity Conditions for Byzantine-Tolerant Federated Learning15 May 2026
- 2026Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AI15 May 2026
- 2026A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions10 May 2026
- 2026Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates10 May 2026
- 2026Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings12 Apr 2026
- 2026Byzantine-Robust Distributed SGD: A Unified Analysis and Tight Error Bounds11 Apr 2026
- 2026Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements7 Apr 2026
- 2026Enhancing Robustness of Federated Learning via Server Learning3 Apr 2026
- 2026FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation30 Mar 2026
- 2026ARMOR: Adaptive Resilience Against Model Poisoning Attacks in Continual Federated Learning for Mobile Indoor Localization20 Mar 2026
- 2026Beyond Weighted Summation: Learnable Nonlinear Aggregation Functions for Robust Artificial Neurons19 Mar 2026
- 2026Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding17 Mar 2026
- 2026Dynamic Meta-Layer Aggregation for Byzantine-Robust Federated Learning17 Mar 2026
- 2026Byzantine-Robust Optimization under (L0, L1)-Smoothness12 Mar 2026
- 2026TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learning10 Mar 2026
- 2026Communication-Efficient Byzantine-Robust Federated Conformal Prediction via Partial Sharing20 Feb 2026
- 2026PenTiDef: Decentralized Federated Intrusion Detection System with Differential Privacy and Latent-Space Defense via Blockchain Coordination in IIoT20 Feb 2026
- 2026Robust Processing and Learning: Principles, Methods, and Wireless Applications10 Feb 2026
- 2026From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity3 Feb 2026
- 2026Topology-Independent Robustness of the Weighted Mean under Label Poisoning Attacks in Heterogeneous Decentralized Learning6 Jan 2026
- 2026FAROS: Robust Federated Learning with Adaptive Scaling against Backdoor Attacks5 Jan 2026
- 2025Zero-Trust Agentic Federated Learning for Secure IIoT Defense Systems29 Dec 2025
- 2025GShield: Mitigating Poisoning Attacks in Federated Learning22 Dec 2025
- 2025FLARE: A Wireless Side-Channel Fingerprinting Attack on Federated Learning11 Dec 2025
- 2025FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization24 Nov 2025
- 2025Accuracy is Not Enough: Poisoning Interpretability in Federated Learning via Color Skew17 Nov 2025
- 2025Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis14 Nov 2025
- 2025Towards Personalized Quantum Federated Learning for Anomaly Detection8 Nov 2025
- 2025Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning4 Nov 2025
50 newest of 314 All 314 (JSON)
- 2023Label Poisoning is All You Needcited by 27
- 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
- 2022Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesiscited by 12
- 2021Meta Federated Learningcited by 8
- 2022Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregationcited by 8
- 2024PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuningcited by 5
- 2024Decaf: Data Distribution Decompose Attack against Federated Learningcited by 4
- 2025Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysiscited by 3
- 2022Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenariocited by 2
- 2023Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verificationcited by 2
- 2023Attacks on fairness in Federated Learningcited by 1
- 2025DROP: Poison Dilution via Knowledge Distillation for Federated Learningcited by 1
12 most cited of 16 All 16 (JSON)
- 2026STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation14 Aug 2026
- 2025Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis14 Nov 2025
- 2025Hybrid Reputation Aggregation: A Robust Defense Mechanism for Adversarial Federated Learning in 5G and Edge Network Environments22 Sep 2025
- 2025FIDELIS: Blockchain-Enabled Protection Against Poisoning Attacks in Federated Learning11 Aug 2025
- 2025FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning23 Feb 2025
- 2025DROP: Poison Dilution via Knowledge Distillation for Federated Learning10 Feb 2025
- 2024PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning28 Nov 2024
- 2024Decaf: Data Distribution Decompose Attack against Federated Learning24 May 2024
- 2023Attacks on fairness in Federated Learning21 Nov 2023
- 2023Label Poisoning is All You Need29 Oct 2023
- 2023Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification6 Oct 2023
- 2022Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario20 Oct 2022
12 newest of 16 All 16 (JSON)
- 2021Robust Federated Learning by Mixture of Expertscited by 4
- 2021Robust Federated Learning by Mixture of Experts23 Apr 2021
- 2021A Field Guide to Federated Optimizationcited by 312
- 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 124
- 2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 123
- 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
- 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
- 2021Federated Quantum Machine Learningcited by 82
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
- 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
- 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 64
- 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
- 2021EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learningcited by 53
12 most cited of 295 All 295 (JSON)
- 2026Robustifying Asynchronous SGD via Soft Throttling30 Sep 2026
- 2026Median Temporal Ensembling: Training-Free Robust Aggregation for Action-Chunked Visuomotor Policies22 Sep 2026
- 2026FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks22 Sep 2026
- 2026On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression22 Sep 2026
- 2026Structural Negative Transfer in Federated Graph Neural Networks: Diagnosis, Causal Investigation, and the Limits of Divergence-Aware Mitigation15 Sep 2026
- 2026Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface3 Sep 2026
- 2026Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning25 Aug 2026
- 2026Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning12 Aug 2026
- 2026Analysis of Federated Aggregation under Model Poisoning and Backdoor Attacks: A Reconstructed Cross-Dataset and Cross-Architecture Benchmark11 Aug 2026
- 2026FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks7 Aug 2026
- 2026Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning6 Aug 2026
- 2026Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning29 Jul 2026
12 newest of 295 All 295 (JSON)