mlsanityData to 7 Oct 2026

Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges

arXiv 2201.08135 ↗First posted 20 Jan 2022cs.CR cs.AI cs.LGcited by 81

Not on the map. Why?

Abstract (arXiv)

Federated learning is a machine learning paradigm that emerges as a solution to the privacy-preservation demands in artificial intelligence. As machine learning, federated learning is threatened by adversarial attacks against the integrity of the learning model and the privacy of data via a distributed approach to tackle local and global learning. This weak point is exacerbated by the inaccessibility of data in federated learning, which makes harder the protection against adversarial attacks and evidences the need to furtherance the research on defence methods to make federated learning a real solution for safeguarding data privacy. In this paper, we present an extensive review of the threats of federated learning, as well as as their corresponding countermeasures, attacks versus defences. This survey provides a taxonomy of adversarial attacks and a taxonomy of defence methods that depict a general picture of this vulnerability of federated learning and how to overcome it. Likewise, we expound guidelines for selecting the most adequate defence method according to the category of the adversarial attack. Besides, we carry out an extensive experimental study from which we draw further conclusions about the behaviour of attacks and defences and the guidelines for selecting the most adequate defence method according to the category of the adversarial attack. This study is finished leading to meditated learned lessons and challenges.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Builds on 98 of its 179 references that are in the map. First posted on arXiv 20 Jan 2022.

Builds on

98 of 179 references.

References · 98

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  8. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  10. 2019Deep Leakage from Gradientscited by 1,004
  11. 2017A Survey on Multi-Task Learningcited by 838
  12. 2018How To Backdoor Federated Learningcited by 745
38 more
  1. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  3. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  4. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  5. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  6. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  7. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  8. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 471
  9. 2021Towards Personalized Federated Learningcited by 462
  10. 2019Federated Machine Learning: Concept and Applicationscited by 409
  11. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  12. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  13. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  14. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  15. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  16. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  17. 2019Robust Aggregation for Federated Learningcited by 314
  18. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  19. 2014Sketching as a Tool for Numerical Linear Algebracited by 285
  20. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  21. 2018Scalable Private Learning with PATEcited by 266
  22. 2019Can You Really Backdoor Federated Learning?cited by 250
  23. 2015Tensorizing Neural Networkscited by 246
  24. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  25. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 234
  26. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  27. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 163
  28. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  29. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  30. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  31. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 125
  32. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
  33. 2019Deep Learning with Gaussian Differential Privacycited by 112
  34. 2020Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Thingscited by 110
  35. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 105
  36. 2020Provable Defense against Privacy Leakage in Federated Learning from Representation Perspectivecited by 94
  37. 2018D"IoT: A Federated Self-learning Anomaly Detection System for IoTcited by 89
  38. 2021Label Leakage and Protection in Two-party Split Learningcited by 87

50 most cited of 98 All 98 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 21; 2024: 26; 2025: 18; 2026: 8.

81 papers.

Sort:

By area:

  1. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 137
  2. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  3. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  4. 2023FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learningcited by 70
  5. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Surveycited by 34
  6. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  7. 2023Integration of Large Language Models and Federated Learningcited by 28
  8. 2023A Survey on Decentralized Federated Learningcited by 27
  9. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  10. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  11. 2024Synergizing Foundation Models and Federated Learning: A Surveycited by 14
  12. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 14
38 more
  1. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
  2. 2023ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learningcited by 9
  3. 2024Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attackscited by 8
  4. 2022A Secure Federated Learning Framework for Residential Short Term Load Forecastingcited by 7
  5. 2022New Challenges in Reinforcement Learning: A Survey of Security and Privacycited by 7
  6. 2022Studying the Robustness of Anti-adversarial Federated Learning Models Detecting Cyberattacks in IoT Spectrum Sensorscited by 5
  7. 2024A Systematic Review of Federated Generative Modelscited by 5
  8. 2024Federated brain tumor segmentation: an extensive benchmarkcited by 5
  9. 2025Energy-Latency Attacks: A New Adversarial Threat to Deep Learningcited by 5
  10. 2023Sentinel: An Aggregation Function to Secure Decentralized Federated Learningcited by 4
  11. 2023Federated Learning for 6G: Paradigms, Taxonomy, Recent Advances and Insightscited by 4
  12. 2024FLEX: FLEXible Federated Learning Frameworkcited by 4
  13. 2024Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspectivecited by 4
  14. 2025Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspectivecited by 4
  15. 2022Edge Security: Challenges and Issuescited by 3
  16. 2023Poisoning Attacks and Defenses in Federated Learning: A Surveycited by 3
  17. 2023Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detectioncited by 3
  18. 2024FedRDF: A Robust and Dynamic Aggregation Function against Poisoning Attacks in Federated Learningcited by 3
  19. 2025Synergizing AI and Digital Twins for Next-Generation Network Optimization, Forecasting, and Securitycited by 3
  20. 2025A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoptioncited by 3
  21. 2025Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontierscited by 3
  22. 2022Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Studycited by 2
  23. 2022Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenariocited by 2
  24. 2023Survey of Federated Learning Models for Spatial-Temporal Mobility Applicationscited by 2
  25. 2023Privacy Preserving Federated Learning with Convolutional Variational Bottleneckscited by 2
  26. 2024Privacy-preserving datasets by capturing feature distributions with Conditional VAEscited by 2
  27. 2025Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distancecited by 2
  28. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  29. 2023Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximizationcited by 1
  30. 2023A Novel Neural Network-Based Federated Learning System for Imbalanced and Non-IID Datacited by 1
  31. 2024Estimation of conditional average treatment effects on distributed confidential datacited by 1
  32. 2024Federated Learning with Flexible Architecturescited by 1
  33. 2024Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defensecited by 1
  34. 2024Celtibero: Robust Layered Aggregation for Federated Learningcited by 1
  35. 2024TPFL: A Trustworthy Personalized Federated Learning Framework via Subjective Logiccited by 1
  36. 2024Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimizationcited by 1
  37. 2024Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learningcited by 1
  38. 2025GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Modelscited by 1

50 most cited of 81 All 81 (JSON)