mlsanityData to 14 Oct 2026

FedIPR: Ownership Verification for Federated Deep Neural Network Models

arXiv 2109.13236 ↗First posted 27 Sep 2021cs.LG cs.AIcited by 36

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

Federated learning models are collaboratively developed upon valuable training data owned by multiple parties. During the development and deployment of federated models, they are exposed to risks including illegal copying, re-distribution, misuse and/or free-riding. To address these risks, the ownership verification of federated learning models is a prerequisite that protects federated learning model intellectual property rights (IPR) i.e., FedIPR. We propose a novel federated deep neural network (FedDNN) ownership verification scheme that allows private watermarks to be embedded and verified to claim legitimate IPR of FedDNN models. In the proposed scheme, each client independently verifies the existence of the model watermarks and claims respective ownership of the federated model without disclosing neither private training data nor private watermark information. The effectiveness of embedded watermarks is theoretically justified by the rigorous analysis of conditions under which watermarks can be privately embedded and detected by multiple clients. Moreover, extensive experimental results on computer vision and natural language processing tasks demonstrate that varying bit-length watermarks can be embedded and reliably detected without compromising original model performances. Our watermarking scheme is also resilient to various federated training settings and robust against removal attacks.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 41 of its 59 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

41 of 59 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Deep Model Intellectual Property Protection via Deep Watermarking8 Mar

Other references · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  6. 2019Advances and Open Problems in Federated Learningcited by 3,046
  7. 2016Deep Learning with Differential Privacycited by 2,728
  8. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  9. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,043
  10. 2019Deep Leakage from Gradientscited by 1,021
  11. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 787
  12. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
28 more
  1. 2018How To Backdoor Federated Learningcited by 765
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  3. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  4. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  5. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  6. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 463
  7. 2019Federated Machine Learning: Concept and Applicationscited by 412
  8. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  9. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  10. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  11. 2013One Billion Word Benchmark for Measuring Progress in Statistical Language Modelingcited by 308
  12. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 292
  13. 2019Can You Really Backdoor Federated Learning?cited by 255
  14. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  15. 2020Blind Backdoors in Deep Learning Modelscited by 182
  16. 2020Threats to Federated Learning: A Surveycited by 178
  17. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  18. 2019Deep Neural Network Fingerprinting by Conferrable Adversarial Examplescited by 93
  19. 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 88
  20. 2020Free-rider Attacks on Model Aggregation in Federated Learningcited by 57
  21. 2019Free-riders in Federated Learning: Attacks and Defensescited by 49
  22. 2020Passport-aware Normalization for Deep Model Protectioncited by 43
  23. 2020Mitigating Backdoor Attacks in Federated Learningcited by 39
  24. 2020WAFFLE: Watermarking in Federated Learningcited by 37
  25. 2018DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networkscited by 26
  26. 2020ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharingcited by 20
  27. 2020Protect, Show, Attend and Tell: Empowering Image Captioning Models with Ownership Protectioncited by 20
  28. 2018DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Modelscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 13; 2024: 3; 2025: 10; 2026: 7.

36 papers.

Sort:

By area:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  2. 2023FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Modelscited by 63
  3. 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 35
  4. 2022FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Modelcited by 30
  5. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  6. 2023Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Surveycited by 18
  7. 2022Tighter Regret Analysis and Optimization of Online Federated Learningcited by 14
  8. 2023FedCIP: Federated Client Intellectual Property Protection with Traitor Trackingcited by 12
  9. 2023FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscationcited by 10
  10. 2023FedZKP: Federated Model Ownership Verification with Zero-knowledge Proofcited by 9
  11. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  12. 2023FedRight: An Effective Model Copyright Protection for Federated Learningcited by 8
24 more
  1. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 7
  2. 2025AugFL: Augmenting Federated Learning with Pretrained Modelscited by 6
  3. 2023FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signaturecited by 4
  4. 2024RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protectioncited by 4
  5. 2023Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectivescited by 3
  6. 2025Traceable Black-box Watermarks for Federated Learningcited by 2
  7. 2023VeryFL: A Verify Federated Learning Framework Embedded with Blockchaincited by 1
  8. 2025Protecting Intellectual Property of EEG-based Neural Networks with Watermarkingcited by 1
  9. 2025FedPoP: Federated Learning Meets Proof of Participationcited by 1
  10. 2026BlackCATT: Black-box Collusion Aware Traitor Tracing in Federated Learningcited by 1
  11. 2026EmbTracker: Traceable Black-box Watermarking for Federated Language Modelscited by 1
  12. 2023Tokenized Model: A Blockchain-Empowered Decentralized Model Ownership Verification Platformcited by 0
  13. 2024FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscationcited by 0
  14. 2024On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairnesscited by 0
  15. 2025PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarkingcited by 0
  16. 2025PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstructioncited by 0
  17. 2025FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learningcited by 0
  18. 2025Robust Client-Server Watermarking for Split Federated Learningcited by 0
  19. 2025Server-Enforced Watermarking in U-Shaped Split Federated Learningcited by 0
  20. 2026Collaborative Threshold Watermarkingcited by 0
  21. 2026Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learningcited by 0
  22. 2026Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Modelscited by 0
  23. 2026FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMscited by 0
  24. 2026ZK-Trace: Certified Collusion Tracing with Zero-Knowledge Credentials for Federated GNSS Interference Monitoringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Regulating Ownership Verification for Deep Neural Networks: Scenarios, Protocols, and Prospects
  2. 2021Towards Practical Watermark for Deep Neural Networks in Federated Learning
  3. 2024Harmless Backdoor-based Client-side Watermarking in Federated Learning
  4. 2021Ownership Verification of DNN Architectures via Hardware Cache Side Channels
  5. 2023VeriDIP: Verifying Ownership of Deep Neural Networks through Privacy Leakage Fingerprints
  6. 2023Turn Passive to Active: A Survey on Active Intellectual Property Protection of Deep Learning Models
  7. 2023OVLA: Neural Network Ownership Verification using Latent Watermarks
  8. 2023Deep Intellectual Property Protection: A Survey