mlsanityData to 14 Oct 2026

Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges

arXiv 2407.06754 ↗First posted 9 Jul 2024cs.DC cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) offers innovative solutions for privacy-preserving collaborative machine learning (ML). Despite its promising potential, FL is vulnerable to various attacks due to its distributed nature, affecting the entire life cycle of FL services. These threats can harm the model's utility or compromise participants' privacy, either directly or indirectly. In response, numerous defense frameworks have been proposed, demonstrating effectiveness in specific settings and scenarios. To provide a clear understanding of the current research landscape, this paper reviews the most representative and state-of-the-art threats and defense frameworks throughout the FL service life cycle. We start by identifying FL threats that harm utility and privacy, including those with potential or direct impacts. Then, we dive into the defense frameworks, analyze the relationship between threats and defenses, and compare the trade-offs among different defense strategies. Finally, we summarize current research bottlenecks and offer insights into future research directions to conclude this survey. We hope this survey sheds light on trustworthy FL research and contributes to the FL community.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 125 of its 269 references that are in the map. First posted on arXiv 9 Jul 2024.

Builds on

125 of 269 references.

References · 125

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2014Going Deeper with Convolutionscited by 4,241
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2019Advances and Open Problems in Federated Learningcited by 3,046
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  10. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  11. 2019Deep Leakage from Gradientscited by 1,021
  12. 2016Adversarial Machine Learning at Scalecited by 936
38 more
  1. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  2. 2018How To Backdoor Federated Learningcited by 765
  3. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  4. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  5. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  6. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  7. 2019Adversarial Training for Free!cited by 643
  8. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  9. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  10. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  11. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  12. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  13. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  14. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  15. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  16. 2020Backdoor Learning: A Surveycited by 426
  17. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  18. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  19. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  20. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  21. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  22. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  23. 2019Robust Aggregation for Federated Learningcited by 317
  24. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  25. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  26. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  27. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  28. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  29. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
  30. 2019Differentially Private Learning with Adaptive Clippingcited by 220
  31. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  32. 2020Membership Leakage in Label-Only Exposurescited by 168
  33. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  34. 2021Towards Understanding Knowledge Distillationcited by 158
  35. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 149
  36. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
  37. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 135
  38. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132

50 most cited of 125 All 125 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 9; 2026: 5.

15 papers.

Sort:

By area:

  1. 2024A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapsecited by 13
  2. 2025Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detectioncited by 8
  3. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
  4. 2025Towards more transferable adversarial attack in black-box mannercited by 2
  5. 2025Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environmentscited by 2
  6. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  7. 2025Towards Adapting Federated & Quantum Machine Learning for Network Intrusion Detection: A Surveycited by 2
  8. 2025Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbationcited by 0
  9. 2025From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0cited by 0
  10. 2025Noise-Aware and Dynamically Adaptive Federated Defense Framework for SAR Image Target Recognitioncited by 0
  11. 2026Topology-Independent Robustness of the Weighted Mean under Label Poisoning Attacks in Heterogeneous Decentralized Learningcited by 0
  12. 2026FL-PBM: Pre-Training Backdoor Mitigation for Federated Learningcited by 0
3 more
  1. 2026On the Fragility of Data Attribution When Learning Is Distributedcited by 0
  2. 2026PCDM: A Diffusion-Based Data Poisoning Attack Against Federated Learning Systemscited by 0
  3. 2026Distributed Quantum Learning over Near-term Devices: Convergence Analysis and Security Designcited by 0