Mitigating Sybils in Federated Learning Poisoning
Not on the map. Why?
Abstract (arXiv)
Machine learning (ML) over distributed multi-party data is required for a variety of domains. Existing approaches, such as federated learning, collect the outputs computed by a group of devices at a central aggregator and run iterative algorithms to train a globally shared model. Unfortunately, such approaches are susceptible to a variety of attacks, including model poisoning, which is made substantially worse in the presence of sybils. In this paper we first evaluate the vulnerability of federated learning to sybil-based poisoning attacks. We then describe FoolsGold, a novel defense to this problem that identifies poisoning sybils based on the diversity of client updates in the distributed learning process. Unlike prior work, our system does not bound the expected number of attackers, requires no auxiliary information outside of the learning process, and makes fewer assumptions about clients and their data. In our evaluation we show that FoolsGold exceeds the capabilities of existing state of the art approaches to countering sybil-based label-flipping and backdoor poisoning attacks. Our results hold for different distributions of client data, varying poisoning targets, and various sybil strategies. Code can be found at: https://github.com/DistributedML/FoolsGold
Key facts. Cited by 158 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Aug 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 29; 2022: 31; 2023: 27; 2024: 24; 2025: 30; 2026: 17.
158 papers.
Sort:
By area:
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
- 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
- 2021Federated Reinforcement Learning: Techniques, Applications, and Open Challengescited by 79
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
- 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
- 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43
- 2023Privacy Side Channels in Machine Learning Systemscited by 38
- 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
- 2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
- 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
38 more
- 2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 29
- 2022TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernelscited by 26
- 2021RoFL: Robustness of Secure Federated Learningcited by 23
- 2021Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learningcited by 21
- 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
- 2021FedAR: Activity and Resource-Aware Federated Learning Model for Distributed Mobile Robotscited by 18
- 2022The Cost of Training Machine Learning Models over Distributed Data Sourcescited by 18
- 2024Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Modelscited by 18
- 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
- 2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
- 2021Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthinesscited 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
- 2022Decentral and Incentivized Federated Learning Frameworks: A Systematic Literature Reviewcited by 15
- 2021Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensuscited by 14
- 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
- 2025Do We Really Need to Design New Byzantine-robust Aggregation Rules?cited by 13
- 2021Untargeted Poisoning Attack Detection in Federated Learning via Behavior Attestationcited by 12
- 2022Federated Learning Attacks and Defenses: A Surveycited by 11
- 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
- 2021Bandwidth Allocation for Multiple Federated Learning Services in Wireless Edge Networkscited by 10
- 2024Poisoning Attacks on Federated Learning-based Wireless Traffic Predictioncited by 10
- 2021FL-Market: Trading Private Models in Federated Learningcited by 9
- 2021RobustFed: A Truth Inference Approach for Robust Federated Learningcited by 9
- 2023Client-specific Property Inference against Secure Aggregation in Federated Learningcited by 9
- 2023BadVFL: Backdoor Attacks in Vertical Federated Learningcited by 9
- 2023G2uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clusteringcited by 9
- 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
- 2021Meta Federated Learningcited by 8
- 2022ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systemscited by 8
- 2022Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensemblingcited by 8
- 2022Personalized Federated Learning via Heterogeneous Modular Networkscited by 8
- 2021Fidel: Reconstructing Private Training Samples from Weight Updates in Federated Learningcited by 7
- 2023A Survey of Federated Evaluation in Federated Learningcited by 7
- 2021Turning Federated Learning Systems Into Covert Channelscited by 6
- 2023Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspectivecited by 6
- 2024Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learningcited by 6
- 2025Federated Learning for Cyber Physical Systems: A Comprehensive Surveycited by 6
50 most cited of 158 All 158 (JSON)
- 2026When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning8 Oct 2026
- 2026When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense22 Sep 2026
- 2026End-to-End Verifiable and Robust Federated Learning14 Sep 2026
- 2026Fine-grained Distributed Backdoor Attacks in Federated Learning7 Sep 2026
- 2026STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation14 Aug 2026
- 2026Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning3 Aug 2026
- 2026Secure Decentralized Federated Learning via Gossip and Virtual Voting9 Jul 2026
- 2026Securing Autonomous Vehicle Systems via Twin-Aware Federated Reinforcement Learning9 Jul 2026
- 2026FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs22 Jun 2026
- 2026Can Quantum Federated Learning Withstand Circuit-Level Backdoors?18 May 2026
- 2026SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions12 May 2026
- 2026FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement11 May 2026
38 more
- 2026XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers10 Apr 2026
- 2026Temperature Scaling Attack Disrupting Model Confidence in Federated Learning6 Feb 2026
- 2026Robust Federated Learning via Byzantine Filtering over Encrypted Updates5 Feb 2026
- 2026Safe-FedLLM: Delving into the Safety of Federated Large Language Models12 Jan 2026
- 2026Byzantine-Robust Federated Learning Framework with Post-Quantum Secure Aggregation for Real-Time Threat Intelligence Sharing in Critical IoT Infrastructure3 Jan 2026
- 2025GShield: Mitigating Poisoning Attacks in Federated Learning22 Dec 2025
- 2025Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning19 Dec 2025
- 2025Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain14 Dec 2025
- 2025On the Fragility of Contribution Score Computation in Federated Learning24 Sep 2025
- 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction23 Sep 2025
- 2025Hybrid Reputation Aggregation: A Robust Defense Mechanism for Adversarial Federated Learning in 5G and Edge Network Environments22 Sep 2025
- 2025ProDiGy: Proximity- and Dissimilarity-Based Byzantine-Robust Federated Learning11 Sep 2025
- 2025Hammer and Anvil: Toward a Theory of Backdoors in Federated Learning9 Sep 2025
- 2025Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor It2 Sep 2025
- 2025Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats30 Aug 2025
- 2025FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning30 Aug 2025
- 2025Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs28 Aug 2025
- 2025FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks26 Aug 2025
- 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions19 Aug 2025
- 2025Decentralized Weather Forecasting via Distributed Machine Learning and Blockchain-Based Model Validation12 Aug 2025
- 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning7 Jul 2025
- 2025Detect & Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learning30 Jun 2025
- 2025Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learning11 Jun 2025
- 2025ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning22 May 2025
- 2025Federated Learning for Cyber Physical Systems: A Comprehensive Survey8 May 2025
- 2025Federated Learning: A Survey on Privacy-Preserving Collaborative Intelligence24 Apr 2025
- 2025Feedback-Enhanced Hallucination-Resistant Vision-Language Model for Real-Time Scene Understanding7 Apr 2025
- 2025WeiDetect: Weibull Distribution-Based Defense against Poisoning Attacks in Federated Learning for Network Intrusion Detection Systems6 Apr 2025
- 2025Enhancing Federated Learning Through Secure Cluster-Weighted Client Aggregation29 Mar 2025
- 2025Multi-Target Federated Backdoor Attack Based on Feature Aggregation23 Feb 2025
- 2025LiveVal: Time-aware Data Valuation via Adaptive Reference Points14 Feb 2025
- 2025DROP: Poison Dilution via Knowledge Distillation for Federated Learning10 Feb 2025
- 2025Do We Really Need to Design New Byzantine-robust Aggregation Rules?29 Jan 2025
- 2025FL-CLEANER: byzantine and backdoor defense by CLustering Errors of Activation maps in Non-iid fedErated leaRning21 Jan 2025
- 2025Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning16 Jan 2025
- 2024Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learning6 Nov 2024
- 2024Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning5 Nov 2024
- 2024Trustworthy Federated Learning: Privacy, Security, and Beyond3 Nov 2024
50 newest of 158 All 158 (JSON)
- 2021Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learningcited by 21
- 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
- 2021Meta Federated Learningcited by 8
- 2022Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenariocited by 2
- 2023Attacks on fairness in Federated Learningcited by 1
- 2025DROP: Poison Dilution via Knowledge Distillation for Federated Learningcited by 1
- 2025Hybrid Reputation Aggregation: A Robust Defense Mechanism for Adversarial Federated Learning in 5G and Edge Network Environmentscited by 1
- 2026STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregationcited by 0
- 2026STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation14 Aug 2026
- 2025Hybrid Reputation Aggregation: A Robust Defense Mechanism for Adversarial Federated Learning in 5G and Edge Network Environments22 Sep 2025
- 2025DROP: Poison Dilution via Knowledge Distillation for Federated Learning10 Feb 2025
- 2023Attacks on fairness in Federated Learning21 Nov 2023
- 2022Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario20 Oct 2022
- 2021Meta Federated Learning10 Feb 2021
- 2021Robust Federated Learning with Attack-Adaptive Aggregation10 Feb 2021
- 2021Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning1 Feb 2021
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
- 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
- 2021Federated Reinforcement Learning: Techniques, Applications, and Open Challengescited by 79
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
- 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
- 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43
- 2023Privacy Side Channels in Machine Learning Systemscited by 38
- 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
- 2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
- 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
12 most cited of 146 All 146 (JSON)
- 2026When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning8 Oct 2026
- 2026When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense22 Sep 2026
- 2026End-to-End Verifiable and Robust Federated Learning14 Sep 2026
- 2026Fine-grained Distributed Backdoor Attacks in Federated Learning7 Sep 2026
- 2026Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning3 Aug 2026
- 2026Secure Decentralized Federated Learning via Gossip and Virtual Voting9 Jul 2026
- 2026Can Quantum Federated Learning Withstand Circuit-Level Backdoors?18 May 2026
- 2026SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions12 May 2026
- 2026FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement11 May 2026
- 2026XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers10 Apr 2026
- 2026Temperature Scaling Attack Disrupting Model Confidence in Federated Learning6 Feb 2026
- 2026Robust Federated Learning via Byzantine Filtering over Encrypted Updates5 Feb 2026
12 newest of 146 All 146 (JSON)