mlsanityData to 7 Oct 2026

Turning Federated Learning Systems Into Covert Channels

arXiv 2104.10561 ↗First posted 21 Apr 2021cs.CR cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) goes beyond traditional, centralized machine learning by distributing model training among a large collection of edge clients. These clients cooperatively train a global, e.g., cloud-hosted, model without disclosing their local, private training data. The global model is then shared among all the participants which use it for local predictions. In this paper, we put forward a novel attacker model aiming at turning FL systems into covert channels to implement a stealth communication infrastructure. The main intuition is that, during federated training, a malicious sender can poison the global model by submitting purposely crafted examples. Although the effect of the model poisoning is negligible to other participants, and does not alter the overall model performance, it can be observed by a malicious receiver and used to transmit a single bit.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 88 references that are in the map. First posted on arXiv 21 Apr 2021.

Builds on

42 of 88 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2019Advances and Open Problems in Federated Learningcited by 3,021
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  10. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  11. 2018How To Backdoor Federated Learningcited by 745
  12. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
30 more
  1. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  2. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  3. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  4. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  5. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  6. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  7. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  8. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  9. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  10. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 202
  11. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  12. 2020Threats to Federated Learning: A Surveycited by 171
  13. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 171
  14. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  15. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
  16. 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 128
  17. 2018Stealing Hyperparameters in Machine Learningcited by 115
  18. 2018Is feature selection secure against training data poisoning?cited by 88
  19. 2016Data Poisoning Attacks on Factorization-Based Collaborative Filteringcited by 78
  20. 2018Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attackscited by 78
  21. 2018Backdooring Convolutional Neural Networks via Targeted Weight Perturbationscited by 66
  22. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 63
  23. 2020Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Frameworkcited by 59
  24. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  25. 2018Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learningcited by 56
  26. 2018Poisoning Attacks to Graph-Based Recommender Systemscited by 52
  27. 2018Model-Reuse Attacks on Deep Learning Systemscited by 47
  28. 2018Exploring Adversarial Examples in Malware Detectioncited by 41
  29. 2018Universal Multi-Party Poisoning Attackscited by 17
  30. 2020VenoMave: Targeted Poisoning Against Speech Recognitioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 0; 2025: 0; 2026: 1.

6 papers.

  1. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  2. 2023A Survey on Decentralized Federated Learningcited by 27
  3. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  4. 2022Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learningcited by 7
  5. 2023Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detectioncited by 3
  6. 2026Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunitiescited by 0