mlsanityData to 7 Oct 2026

Privacy and Trust Redefined in Federated Machine Learning

arXiv 2103.15753 ↗First posted 29 Mar 2021cs.CR cs.CY cs.DCcited by 13

Not on the map. Why?

Abstract (arXiv)

A common privacy issue in traditional machine learning is that data needs to be disclosed for the training procedures. In situations with highly sensitive data such as healthcare records, accessing this information is challenging and often prohibited. Luckily, privacy-preserving technologies have been developed to overcome this hurdle by distributing the computation of the training and ensuring the data privacy to their owners. The distribution of the computation to multiple participating entities introduces new privacy complications and risks. In this paper, we present a privacy-preserving decentralised workflow that facilitates trusted federated learning among participants. Our proof-of-concept defines a trust framework instantiated using decentralised identity technologies being developed under Hyperledger projects Aries/Indy/Ursa. Only entities in possession of Verifiable Credentials issued from the appropriate authorities are able to establish secure, authenticated communication channels authorised to participate in a federated learning workflow related to mental health data.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 52 of its 134 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

52 of 134 references.

References · 52

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  8. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  10. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  11. 2019Towards Federated Learning at Scale: System Designcited by 826
  12. 2018How To Backdoor Federated Learningcited by 745
38 more
  1. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  2. 2017Renyi Differential Privacycited by 643
  3. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  4. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
  5. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  6. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  7. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  8. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  9. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  10. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  11. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  12. 2017Certified Defenses for Data Poisoning Attackscited by 288
  13. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  14. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  15. 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 188
  16. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  17. 2017Machine Learning Models that Remember Too Muchcited by 165
  18. 2018Activation Functions: Comparison of trends in Practice and Research for Deep Learningcited by 130
  19. 2019Overcoming Forgetting in Federated Learning on Non-IID Datacited by 120
  20. 2016An Analysis of Deep Neural Network Models for Practical Applicationscited by 114
  21. 2018A generic framework for privacy preserving deep learningcited by 103
  22. 2018A General Approach to Adding Differential Privacy to Iterative Training Procedurescited by 84
  23. 2018Privacy Preserving Machine Learning: Threats and Solutionscited by 78
  24. 2014Learning Activation Functions to Improve Deep Neural Networkscited by 62
  25. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  26. 2019Local Differential Privacy for Deep Learningcited by 46
  27. 2014An introduction to Docker for reproducible research, with examples from the R environmentcited by 25
  28. 2018Privacy-preserving Machine Learning through Data Obfuscationcited by 18
  29. 2020FedFMC: Sequential Efficient Federated Learning on Non-iid Datacited by 17
  30. 2020Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learningcited by 12
  31. 2016Curie: A method for protecting SVM Classifier from Poisoning Attackcited by 9
  32. 2016Distributed Deep Learning Using Synchronous Stochastic Gradient Descentcited by 8
  33. 2017Performance Comparison of Intrusion Detection Systems and Application of Machine Learning to Snort Systemcited by 8
  34. 2020A Distributed Trust Framework for Privacy-Preserving Machine Learningcited by 7
  35. 2018A Review of Homomorphic Encryption Libraries for Secure Computationcited by 4
  36. 2018A First Look at Identity Management Schemes on the Blockchaincited by 2
  37. 2020A Privacy-Preserving Healthcare Framework Using Hyperledger Fabriccited by 2
  38. 2020Trust-by-Design: Evaluating Issues and Perceptions within Clinical Passportingcited by 1

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 1; 2023: 3; 2024: 2; 2025: 2; 2026: 1.

13 papers.

Sort:

  1. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  2. 2021PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNNcited by 35
  3. 2021Practical Defences Against Model Inversion Attacks for Split Neural Networkscited by 29
  4. 2023Recent Methodological Advances in Federated Learning for Healthcarecited by 11
  5. 2025Federated Learning for Cyber Physical Systems: A Comprehensive Surveycited by 6
  6. 2025A Thorough Assessment of the Non-IID Data Impact in Federated Learningcited by 5
  7. 2023Trustworthy Federated Learning: A Surveycited by 4
  8. 2021Providing Assurance and Scrutability on Shared Data and Machine Learning Models with Verifiable Credentialscited by 3
  9. 2024A Comprehensive Survey and Classification of Evaluation Criteria for Trustworthy Artificial Intelligencecited by 3
  10. 2024Federated Learning in Healthcare: Model Misconducts, Security, Challenges, Applications, and Future Research Directions -- A Systematic Reviewcited by 1
  11. 2022Differential Privacy: What is all the noise about?cited by 0
  12. 2023AI Product Security: A Primer for Developerscited by 0
1 more
  1. 2026SoK: A Systematic Bidirectional Literature Review of AI & DLT Convergencecited by 0