mlsanityData to 14 Oct 2026

Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey

arXiv 2312.08667 ↗First posted 14 Dec 2023cs.CR cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Due to the greatly improved capabilities of devices, massive data, and increasing concern about data privacy, Federated Learning (FL) has been increasingly considered for applications to wireless communication networks (WCNs). Wireless FL (WFL) is a distributed method of training a global deep learning model in which a large number of participants each train a local model on their training datasets and then upload the local model updates to a central server. However, in general, non-independent and identically distributed (non-IID) data of WCNs raises concerns about robustness, as a malicious participant could potentially inject a "backdoor" into the global model by uploading poisoned data or models over WCN. This could cause the model to misclassify malicious inputs as a specific target class while behaving normally with benign inputs. This survey provides a comprehensive review of the latest backdoor attacks and defense mechanisms. It classifies them according to their targets (data poisoning or model poisoning), the attack phase (local data collection, training, or aggregation), and defense stage (local training, before aggregation, during aggregation, or after aggregation). The strengths and limitations of existing attack strategies and defense mechanisms are analyzed in detail. Comparisons of existing attack methods and defense designs are carried out, pointing to noteworthy findings, open challenges, and potential future research directions related to security and privacy of WFL.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 123 of its 266 references that are in the map. First posted on arXiv 14 Dec 2023.

Builds on

123 of 266 references.

References · 123

  1. 2016Deep Learning with Differential Privacycited by 2,728
  2. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  5. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  6. 2018How To Backdoor Federated Learningcited by 765
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  9. 2020Backdoor Learning: A Surveycited by 426
  10. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  11. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  12. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
38 more
  1. 2019Hidden Trigger Backdoor Attackscited by 371
  2. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 353
  3. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  4. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  5. 2020Input-Aware Dynamic Backdoor Attackcited by 313
  6. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  7. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  8. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  9. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 263
  10. 2019Can You Really Backdoor Federated Learning?cited by 255
  11. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  12. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  13. 2020BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvementscited by 211
  14. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  15. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 180
  16. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 169
  17. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  18. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 161
  19. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 151
  20. 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 139
  21. 2020Backdoor Attacks Against Deep Learning Systems in the Physical Worldcited by 134
  22. 2019Federated Learning for Wireless Communications: Motivation, Opportunities and Challengescited by 129
  23. 2020Backdoor Attacks to Graph Neural Networkscited by 128
  24. 2020Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Reviewcited by 123
  25. 2021BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learningcited by 123
  26. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 118
  27. 2020Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attackscited by 116
  28. 2020Certified Robustness to Label-Flipping Attacks via Randomized Smoothingcited by 108
  29. 2021Backdoor Scanning for Deep Neural Networks through K-Arm Optimizationcited by 98
  30. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
  31. 2020Communication-Efficient Edge AI: Algorithms and Systemscited by 96
  32. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  33. 2021Integrated Sensing and Communications: Towards Dual-functional Wireless Networks for 6G and Beyondcited by 91
  34. 2021Backdoor Attacks on Self-Supervised Learningcited by 90
  35. 2020Learning to Detect Malicious Clients for Robust Federated Learningcited by 88
  36. 2020Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identificationcited by 86
  37. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  38. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81

50 most cited of 123 All 123 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 7; 2026: 6.

18 papers.

Sort:

By area:

  1. 2025NoT: Federated Unlearning via Weight Negationcited by 15
  2. 2024Vertical Federated Unlearning via Backdoor Certificationcited by 6
  3. 2024The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggerscited by 3
  4. 2025Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agentscited by 3
  5. 2025Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Thingscited by 1
  6. 2025Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coresetcited by 1
  7. 2026A Secure and Private Distributed Bayesian Federated Learning Designcited by 1
  8. 2026AI-Native Closed-Loop Security for 6G-Enabled Cyber-Physical Systems: From Edge Detection to Network-Wide Mitigationcited by 1
  9. 2024Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"cited by 0
  10. 2024Defending Against Neural Network Model Inversion Attacks via Data Poisoningcited by 0
  11. 2024Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learningcited by 0
  12. 2025FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learningcited by 0
6 more
  1. 2025Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updatescited by 0
  2. 2025Hammer and Anvil: Toward a Theory of Backdoors in Federated Learningcited by 0
  3. 2026TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learningcited by 0
  4. 2026Federated Multi Agent Deep Learning and Neural Networks for Advanced Distributed Sensing in Wireless Networkscited by 0
  5. 2026Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoningcited by 0
  6. 2026Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embeddingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networks
  2. 2024Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities
  3. 2024Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
  4. 2024Securing Federated Learning against Backdoor Threats with Foundation Model Integration
  5. 2022Federated Learning based on Defending Against Data Poisoning Attacks in IoT
  6. 2025SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
  7. 2023Mitigating Backdoors in Federated Learning with FLD
  8. 2026Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning