mlsanityData to 7 Oct 2026

Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions

arXiv 2303.02213 ↗First posted 3 Mar 2023cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a machine learning (ML) approach that allows the use of distributed data without compromising personal privacy. However, the heterogeneous distribution of data among clients in FL can make it difficult for the orchestration server to validate the integrity of local model updates, making FL vulnerable to various threats, including backdoor attacks. Backdoor attacks involve the insertion of malicious functionality into a targeted model through poisoned updates from malicious clients. These attacks can cause the global model to misbehave on specific inputs while appearing normal in other cases. Backdoor attacks have received significant attention in the literature due to their potential to impact real-world deep learning applications. However, they have not been thoroughly studied in the context of FL. In this survey, we provide a comprehensive survey of current backdoor attack strategies and defenses in FL, including a comprehensive analysis of different approaches. We also discuss the challenges and potential future directions for attacks and defenses in the context of FL.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 70 of its 131 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

70 of 131 references.

References · 70

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2019Machine Unlearningcited by 1,020
  4. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  5. 2019Towards Federated Learning at Scale: System Designcited by 826
  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. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  10. 2020Backdoor Learning: A Surveycited by 412
  11. 2019Federated Machine Learning: Concept and Applicationscited by 409
  12. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
38 more
  1. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  2. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  3. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  4. 2019Robust Aggregation for Federated Learningcited by 314
  5. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  6. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  7. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  8. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  9. 2019Can You Really Backdoor Federated Learning?cited by 250
  10. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  11. 2020Threats to Federated Learning: A Surveycited by 171
  12. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 171
  13. 2021Adaptive Machine Unlearningcited by 164
  14. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  15. 2020Backdoor Attacks Against Deep Learning Systems in the Physical Worldcited by 129
  16. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 119
  17. 2021Federated Unlearning via Class-Discriminative Pruningcited by 108
  18. 2019Towards Explainable Artificial Intelligencecited by 106
  19. 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 99
  20. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  21. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  22. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?cited by 90
  23. 2018D"IoT: A Federated Self-learning Anomaly Detection System for IoTcited by 89
  24. 2020Privacy Preserving Vertical Federated Learning for Tree-based Modelscited by 89
  25. 2020Learning to Detect Malicious Clients for Robust Federated Learningcited by 86
  26. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  27. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  28. 2018In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learningcited by 80
  29. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  30. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  31. 2022Federated Unlearning with Knowledge Distillationcited by 70
  32. 2021FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysiscited by 60
  33. 2017Generating Steganographic Images via Adversarial Trainingcited by 57
  34. 2020Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approachcited by 56
  35. 2022Vertical Federated Learning: Challenges, Methodologies and Experimentscited by 55
  36. 2019Practical Federated Gradient Boosting Decision Treescited by 53
  37. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 52
  38. 2019Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinatorcited by 51

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 13; 2025: 9; 2026: 7.

33 papers.

Sort:

By area:

  1. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
  2. 2024A Survey of Recent Backdoor Attacks and Defenses in Large Language Modelscited by 36
  3. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  4. 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivitycited by 11
  5. 2024Exploring Vulnerabilities and Protections in Large Language Models: A Surveycited by 10
  6. 2023G2uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clusteringcited by 9
  7. 2023Exploring adversarial attacks in federated learning for medical imagingcited by 8
  8. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  9. 2024Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspectivecited by 4
  10. 2024Flatness-aware Sequential Learning Generates Resilient Backdoorscited by 3
  11. 2024FedBlock: A Blockchain Approach to Federated Learning against Backdoor Attackscited by 2
  12. 2025Multi-Target Federated Backdoor Attack Based on Feature Aggregationcited by 2
21 more
  1. 2026Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learningcited by 2
  2. 2024GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learningcited by 1
  3. 2024Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscapecited by 1
  4. 2024PBP: Post-training Backdoor Purification for Malware Classifierscited by 1
  5. 2025Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Thingscited by 1
  6. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learningcited by 1
  7. 2025BadFU: Backdoor Federated Learning through Adversarial Machine Unlearningcited by 1
  8. 2026BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Drivingcited by 1
  9. 2024Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimizationcited by 0
  10. 2024LOGSAFE: Logic-Guided Verification for Trustworthy Federated Time-Series Learningcited by 0
  11. 2024FedSECA: Sign Election and Coordinate-wise Aggregation of Gradients for Byzantine Tolerant Federated Learningcited by 0
  12. 2025FL-CLEANER: byzantine and backdoor defense by CLustering Errors of Activation maps in Non-iid fedErated leaRningcited by 0
  13. 2025Hammer and Anvil: Toward a Theory of Backdoors in Federated Learningcited by 0
  14. 2025Power to the Clients: Federated Learning in a Dictatorship Settingcited by 0
  15. 2025RobustFSM: Submodular Maximization in Federated Setting with Malicious Clientscited by 0
  16. 2025Unveiling Hidden Threats: Using Fractal Triggers to Boost Stealthiness of Distributed Backdoor Attacks in Federated Learningcited by 0
  17. 2026FL-PBM: Pre-Training Backdoor Mitigation for Federated Learningcited by 0
  18. 2026FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitizationcited by 0
  19. 2026Rethinking Molecular Graph Backdoors under Chemistry-aware Admissioncited by 0
  20. 2026FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defensecited by 0
  21. 2026BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learningcited by 0