mlsanityData to 7 Oct 2026

When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection

arXiv 2308.03573 ↗First posted 7 Aug 2023cs.CR cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a technique that allows multiple participants to collaboratively train a Deep Neural Network (DNN) without the need of centralizing their data. Among other advantages, it comes with privacy-preserving properties making it attractive for application in sensitive contexts, such as health care or the military. Although the data are not explicitly exchanged, the training procedure requires sharing information about participants' models. This makes the individual models vulnerable to theft or unauthorized distribution by malicious actors. To address the issue of ownership rights protection in the context of Machine Learning (ML), DNN Watermarking methods have been developed during the last five years. Most existing works have focused on watermarking in a centralized manner, but only a few methods have been designed for FL and its unique constraints. In this paper, we provide an overview of recent advancements in Federated Learning watermarking, shedding light on the new challenges and opportunities that arise in this field.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 59 of its 130 references that are in the map. First posted on arXiv 7 Aug 2023.

Builds on

59 of 130 references.

References · 59

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  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. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2018Federated Learning with Non-IID Datacited by 1,099
  8. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  9. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  10. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  11. 2020The Future of Digital Health with Federated Learningcited by 625
  12. 2019Object Detection in 20 Years: A Surveycited by 528
38 more
  1. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  2. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  3. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  4. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  5. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  6. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  7. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  8. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 247
  9. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  10. 2017Machine Learning Models that Remember Too Muchcited by 165
  11. 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 115
  12. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
  13. 2020Learning to Detect Malicious Clients for Robust Federated Learningcited by 86
  14. 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 82
  15. 2022NVIDIA FLARE: Federated Learning from Simulation to Real-Worldcited by 78
  16. 2021A survey of deep neural network watermarking techniquescited by 69
  17. 2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 67
  18. 2023Federated Learning of Gboard Language Models with Differential Privacycited by 64
  19. 2019How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNNcited by 58
  20. 2020DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environmentscited by 57
  21. 2020IBM Federated Learning: an Enterprise Framework White Paper V0.1cited by 57
  22. 2021TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryptioncited by 51
  23. 2020A Systematic Review on Model Watermarking for Neural Networkscited by 49
  24. 2019Robust Watermarking of Neural Network with Exponential Weightingcited by 48
  25. 2021Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryptioncited by 46
  26. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
  27. 2020Passport-aware Normalization for Deep Model Protectioncited by 42
  28. 2023FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning Systemcited by 38
  29. 2020WAFFLE: Watermarking in Federated Learningcited by 34
  30. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 33
  31. 2019BlackMarks: Blackbox Multibit Watermarking for Deep Neural Networkscited by 25
  32. 2022FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Modelcited by 25
  33. 2020Spread-Transform Dither Modulation Watermarking of Deep Neural Networkcited by 23
  34. 2020Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learningcited by 19
  35. 2022Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooringcited by 14
  36. 2018Have You Stolen My Model? Evasion Attacks Against Deep Neural Network Watermarking Techniquescited by 10
  37. 2023Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applicationscited by 10
  38. 2020Dynamic backdoor attacks against federated learningcited by 9

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

6 papers.

  1. 2025Watermarking Graph Neural Networks via Explanations for Ownership Protectioncited by 3
  2. 2025FL-CLEANER: byzantine and backdoor defense by CLustering Errors of Activation maps in Non-iid fedErated leaRningcited by 0
  3. 2025FedGAI: Federated Style Learning with Cloud-Edge Collaboration for Generative AI in Fashion Designcited by 0
  4. 2025Traceable Black-box Watermarks for Federated Learningcited by 0
  5. 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
  6. 2026Collaborative Threshold Watermarkingcited by 0