mlsanityData to 7 Oct 2026

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks

arXiv 2106.08283 ↗First posted 15 Jun 2021cs.LGcited by 91

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) as a distributed learning paradigm that aggregates information from diverse clients to train a shared global model, has demonstrated great success. However, malicious clients can perform poisoning attacks and model replacement to introduce backdoors into the trained global model. Although there have been intensive studies designing robust aggregation methods and empirical robust federated training protocols against backdoors, existing approaches lack robustness certification. This paper provides the first general framework, Certifiably Robust Federated Learning (CRFL), to train certifiably robust FL models against backdoors. Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude. Our certification also specifies the relation to federated learning parameters, such as poisoning ratio on instance level, number of attackers, and training iterations. Practically, we conduct comprehensive experiments across a range of federated datasets, and provide the first benchmark for certified robustness against backdoor attacks in federated learning. Our code is available at https://github.com/AI-secure/CRFL.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

25 of 44 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2018Federated Learning with Non-IID Datacited by 1,099
  6. 2018How To Backdoor Federated Learningcited by 745
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  8. 2017Federated Multi-Task Learningcited by 669
  9. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  10. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  12. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
13 more
  1. 2019Robust Aggregation for Federated Learningcited by 314
  2. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  3. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  4. 2019Can You Really Backdoor Federated Learning?cited by 250
  5. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 157
  6. 2020RAB: Provable Robustness Against Backdoor Attackscited by 115
  7. 2018Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithmscited by 106
  8. 2020Robust Federated Learning: The Case of Affine Distribution Shiftscited by 102
  9. 2017Efficient Private ERM for Smooth Objectivescited by 61
  10. 2021Provably Secure Federated Learning against Malicious Clientscited by 60
  11. 2017Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descentcited by 59
  12. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 52
  13. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 17; 2023: 31; 2024: 18; 2025: 17; 2026: 4.

91 papers.

Sort:

By area:

  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  2. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 124
  3. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  4. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  5. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 65
  6. 2024Byzantine-Robust Decentralized Federated Learningcited by 47
  7. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  8. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  9. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  10. 2024Test-Time Backdoor Attacks on Multimodal Large Language Modelscited by 35
  11. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  12. 2022FLCert: Provably Secure Federated Learning against Poisoning Attackscited by 29
38 more
  1. 2023On the Vulnerability of Backdoor Defenses for Federated Learningcited by 27
  2. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  3. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  4. 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
  5. 2023Backdoor Attacks Against Dataset Distillationcited by 20
  6. 2023Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learningcited by 20
  7. 2023FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMscited by 19
  8. 2022Backdoor Cleansing with Unlabeled Datacited by 17
  9. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  10. 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
  11. 2023Fusion of Global and Local Knowledge for Personalized Federated Learningcited by 14
  12. 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attackscited by 12
  13. 2023BadVFL: Backdoor Attacks in Vertical Federated Learningcited by 9
  14. 2023G2uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clusteringcited by 9
  15. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  16. 2024COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuitscited by 9
  17. 2022Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspectivecited by 8
  18. 2022Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregationcited by 8
  19. 2024Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attackscited by 8
  20. 2022Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated Learningcited by 7
  21. 2024Robustness Inspired Graph Backdoor Defensecited by 7
  22. 2021Certified Federated Adversarial Trainingcited by 6
  23. 2023Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspectivecited by 6
  24. 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
  25. 2024Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guaranteecited by 6
  26. 2022Towards a Defense Against Federated Backdoor Attacks Under Continuous Trainingcited by 5
  27. 2022Securing Federated Learning against Overwhelming Collusive Attackerscited by 5
  28. 2023AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplificationcited by 5
  29. 2022Cerberus: Exploring Federated Prediction of Security Eventscited by 4
  30. 2023STDLens: Model Hijacking-Resilient Federated Learning for Object Detectioncited by 4
  31. 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspectioncited by 4
  32. 2023Trustworthy Federated Learning: A Surveycited by 4
  33. 2023Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Networkcited by 4
  34. 2023FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attackscited by 4
  35. 2023FLTracer: Accurate Poisoning Attack Provenance in Federated Learningcited by 4
  36. 2024Identify Backdoored Model in Federated Learning via Individual Unlearningcited by 4
  37. 2021PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacycited by 3
  38. 2023Online Robust Mean Estimationcited by 3

50 most cited of 91 All 91 (JSON)