mlsanityData to 7 Oct 2026

SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification

arXiv 2112.06274 ↗First posted 12 Dec 2021cs.LG cs.AI cs.CRcited by 46

Not on the map. Why?

Abstract (arXiv)

Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on targeted sub-tasks (e.g. classifying planes as birds) by uploading "poisoned" updates. In this report we introduce algoname, a novel defense that uses global top-k update sparsification and device-level gradient clipping to mitigate model poisoning attacks. We propose a theoretical framework for analyzing the robustness of defenses against poisoning attacks, and provide robustness and convergence analysis of our algorithm. To validate its empirical efficacy we conduct an open-source evaluation at scale across multiple benchmark datasets for computer vision and federated learning.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 34 of its 46 references that are in the map. First posted on arXiv 12 Dec 2021.

Builds on

34 of 46 references.

References · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  7. 2018Federated Learning with Non-IID Datacited by 1,099
  8. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  9. 2019Towards Federated Learning at Scale: System Designcited by 826
  10. 2018LEAF: A Benchmark for Federated Settingscited by 780
  11. 2018How To Backdoor Federated Learningcited by 745
  12. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
22 more
  1. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  2. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  4. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 471
  5. 2018Sparsified SGD with Memorycited by 373
  6. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  7. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  8. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  9. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  10. 2019Error Feedback Fixes SignSGD and other Gradient Compression Schemescited by 306
  11. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  12. 2019Can You Really Backdoor Federated Learning?cited by 250
  13. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 178
  14. 2020RAB: Provable Robustness Against Backdoor Attackscited by 115
  15. 2020Deep Partition Aggregation: Provable Defense against General Poisoning Attackscited by 112
  16. 2020Certified Robustness to Label-Flipping Attacks via Randomized Smoothingcited by 103
  17. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  18. 2020Intrinsic Certified Robustness of Bagging against Data Poisoning Attackscited by 90
  19. 2020On Certifying Robustness against Backdoor Attacks via Randomized Smoothingcited by 74
  20. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  21. 2021Provably Secure Federated Learning against Malicious Clientscited by 60
  22. 2019Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithmscited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 13; 2024: 11; 2025: 10; 2026: 3.

46 papers.

Sort:

By area:

  1. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  2. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  3. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  4. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  5. 2024Teach LLMs to Phish: Stealing Private Information from Language Modelscited by 29
  6. 2022On the Impossible Safety of Large AI Modelscited by 27
  7. 2025Data Poisoning in Deep Learning: A Surveycited by 20
  8. 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 13
  9. 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspectioncited by 13
  10. 2023Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learningcited by 12
  11. 2024Trustworthy Distributed AI Systems: Robustness, Privacy, and Governancecited by 12
  12. 2022A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimizationcited by 11
34 more
  1. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
  2. 2023Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learningcited by 9
  3. 2022Federated Progressive Sparsification (Purge, Merge, Tune)+cited by 8
  4. 2023Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacycited by 8
  5. 2023Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Datacited by 7
  6. 2025MARS: A Malignity-Aware Backdoor Defense in Federated Learningcited by 7
  7. 2022FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Datacited by 6
  8. 2024EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learningcited by 4
  9. 2023A Survey on Secure and Private Federated Learning Using Blockchain: Theory and Application in Resource-constrained Computingcited by 3
  10. 2024Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilitiescited by 3
  11. 2025A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networkscited by 3
  12. 2022Invariant Aggregator for Defending against Federated Backdoor Attackscited by 2
  13. 2024Poisoning with A Pill: Circumventing Detection in Federated Learningcited by 2
  14. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  15. 2025FedSparQ: Adaptive Sparse Quantization with Error Feedback for Robust & Efficient Federated Learningcited by 2
  16. 2022Communication-Efficient {Federated} Learning Using Censored Heavy Ball Descentcited by 1
  17. 2022Robust Learning Protocol for Federated Tumor Segmentation Challengecited by 1
  18. 2023Unlocking the Potential of Federated Learning for Deeper Modelscited by 1
  19. 2023Can We Trust the Similarity Measurement in Federated Learning?cited by 1
  20. 2024Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attackcited by 1
  21. 2023A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learningcited by 0
  22. 2023CRS-FL: Conditional Random Sampling for Communication-Efficient and Privacy-Preserving Federated Learningcited by 0
  23. 2023FTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learningcited by 0
  24. 2023The Landscape of Modern Machine Learning: A Review of Machine, Distributed and Federated Learningcited by 0
  25. 2024A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learningcited by 0
  26. 2024Random Gradient Masking as a Defensive Measure to Deep Leakage in Federated Learningcited by 0
  27. 2024Privacy Attack in Federated Learning is Not Easy: An Experimental Studycited by 0
  28. 2025Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Oddscited by 0
  29. 2025Traceable Black-box Watermarks for Federated Learningcited by 0
  30. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinctioncited by 0
  31. 2025Trade-off in Estimating the Number of Byzantine Clients in Federated Learningcited by 0
  32. 2026From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learningcited by 0
  33. 2026Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learningcited by 0
  34. 2026TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learningcited by 0