mlsanityData to 14 Oct 2026

Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation

arXiv 1903.03936 ↗First posted 10 Mar 2019cs.LG cs.CR cs.DCcited by 141

Not on the map. Why?

Abstract (arXiv)

Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robust aggregation methods for synchronous SGD -- coordinate-wise median and Krum -- can be broken using new attack strategies based on inner product manipulation. We prove our results theoretically, as well as show empirical validation.

Key facts. Cited by 141 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 17; 2023: 29; 2024: 37; 2025: 27; 2026: 16.

141 papers.

Sort:

By area:

  1. 2021A Field Guide to Federated Optimizationcited by 315
  2. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  3. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
  4. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 65
  5. 2021Provably Secure Federated Learning against Malicious Clientscited by 63
  6. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  7. 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
  8. 2022Byzantine-Robust Decentralized Learning via ClippedGossipcited by 31
  9. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 30
  10. 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
  11. 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneitycited by 26
  12. 2021RoFL: Robustness of Secure Federated Learningcited by 25
38 more
  1. 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learningcited by 24
  2. 2023FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMscited by 21
  3. 2021Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?cited by 18
  4. 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
  5. 2022An Equivalence Between Data Poisoning and Byzantine Gradient Attackscited by 16
  6. 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
  7. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 15
  8. 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 15
  9. 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splittingcited by 14
  10. 2024Trustworthy Distributed AI Systems: Robustness, Privacy, and Governancecited by 14
  11. 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updatescited by 14
  12. 2021Data Poisoning Attacks and Defenses to Crowdsourcing Systemscited by 12
  13. 2021Secure Distributed Training at Scalecited by 12
  14. 2021Secure Byzantine-Robust Distributed Learning via Clusteringcited by 12
  15. 2022Robust Collaborative Learning with Linear Gradient Overheadcited by 12
  16. 2022Federated Learning Attacks and Defenses: A Surveycited by 12
  17. 2023Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Ratescited by 12
  18. 2023Provably Personalized and Robust Federated Learningcited by 11
  19. 2024Adaptive Gradient Clipping for Robust Federated Learningcited by 11
  20. 2023Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learningcited by 10
  21. 2024MedBN: Robust Test-Time Adaptation against Malicious Test Samplescited by 10
  22. 2024Poisoning Attacks on Federated Learning-based Wireless Traffic Predictioncited by 10
  23. 2023Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneitycited by 9
  24. 2024Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attackscited by 9
  25. 2021Byzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model Updatescited by 8
  26. 2022Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learningcited by 8
  27. 2023Secure Federated Learning against Model Poisoning Attacks via Client Filteringcited by 8
  28. 2024Unified Breakdown Analysis for Byzantine Robust Gossipcited by 8
  29. 2025Towards Trustworthy Federated Learning with Untrusted Participantscited by 8
  30. 2021Byzantine Fault-Tolerance in Federated Local SGD under 2f-Redundancycited by 7
  31. 2022BOBA: Byzantine-Robust Federated Learning with Label Skewnesscited by 7
  32. 2023A First Order Meta Stackelberg Method for Robust Federated Learningcited by 7
  33. 2023Can Decentralized Learning be more robust than Federated Learning?cited by 6
  34. 2024FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learningcited by 6
  35. 2025Federated Learning for Cyber Physical Systems: A Comprehensive Surveycited by 6
  36. 2022SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learningcited by 5
  37. 2022MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attackscited by 5
  38. 2024Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workerscited by 5

50 most cited of 141 All 141 (JSON)