mlsanityData to 7 Oct 2026

Analyzing Federated Learning through an Adversarial Lens

arXiv 1811.12470 ↗First posted 29 Nov 2018cs.LG cs.AI cs.CRcited by 346

Not on the map. Why?

Cited by 38 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this work, we explore the threat of model poisoning attacks on federated learning initiated by a single, non-colluding malicious agent where the adversarial objective is to cause the model to misclassify a set of chosen inputs with high confidence. We explore a number of strategies to carry out this attack, starting with simple boosting of the malicious agent's update to overcome the effects of other agents' updates. To increase attack stealth, we propose an alternating minimization strategy, which alternately optimizes for the training loss and the adversarial objective. We follow up by using parameter estimation for the benign agents' updates to improve on attack success. Finally, we use a suite of interpretability techniques to generate visual explanations of model decisions for both benign and malicious models and show that the explanations are nearly visually indistinguishable. Our results indicate that even a highly constrained adversary can carry out model poisoning attacks while simultaneously maintaining stealth, thus highlighting the vulnerability of the federated learning setting and the need to develop effective defense strategies.

Key facts. Cited by 346 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 69; 2022: 71; 2023: 65; 2024: 61; 2025: 50; 2026: 29.

346 papers.

Sort:

By area:

  1. 2021A Field Guide to Federated Optimizationcited by 312
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 119
  4. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  5. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  6. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  7. 2022Truth Serum: Poisoning Machine Learning Models to Reveal Their Secretscited by 94
  8. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  9. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  10. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  11. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  12. 2022Federated Unlearning with Knowledge Distillationcited by 70
38 more
  1. 2021FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learningcited by 67
  2. 2021BACKDOORL: Backdoor Attack against Competitive Reinforcement Learningcited by 66
  3. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
  4. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 65
  5. 2021Provably Secure Federated Learning against Malicious Clientscited by 60
  6. 2021Property Inference From Poisoningcited by 56
  7. 2021Decentralized Federated Learning through Proxy Model Sharingcited by 56
  8. 2022FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Informationcited by 53
  9. 2021Adversarial Attacks On Multi-Agent Communicationcited by 48
  10. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  11. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  12. 2020Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Expertscited by 43
  13. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 41
  14. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  15. 2021PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotioncited by 37
  16. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  17. 2021Federated Learning for Malware Detection in IoT Devicescited by 36
  18. 2021FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspectivecited by 35
  19. 2022Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directionscited by 34
  20. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 33
  21. 2022PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learningcited by 33
  22. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  23. 2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
  24. 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
  25. 2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 29
  26. 2022FLCert: Provably Secure Federated Learning against Poisoning Attackscited by 29
  27. 2022AFLGuard: Byzantine-robust Asynchronous Federated Learningcited by 29
  28. 2024Teach LLMs to Phish: Stealing Private Information from Language Modelscited by 29
  29. 2023On the Vulnerability of Backdoor Defenses for Federated Learningcited by 27
  30. 2023A Survey on Decentralized Federated Learningcited by 27
  31. 2021Convergence Analysis and System Design for Federated Learning over Wireless Networkscited by 25
  32. 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
  33. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  34. 2021RoFL: Robustness of Secure Federated Learningcited by 23
  35. 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
  36. 2021Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learningcited by 21
  37. 2021GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learningcited by 21
  38. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21

50 most cited of 346 All 346 (JSON)