mlsanityData to 14 Oct 2026

Robust Client-Server Watermarking for Split Federated Learning

arXiv 2511.13598 ↗First posted 17 Nov 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Split Federated Learning (SFL) is renowned for its privacy-preserving nature and low computational overhead among decentralized machine learning paradigms. In this framework, clients employ lightweight models to process private data locally and transmit intermediate outputs to a powerful server for further computation. However, SFL is a double-edged sword: while it enables edge computing and enhances privacy, it also introduces intellectual property ambiguity as both clients and the server jointly contribute to training. Existing watermarking techniques fail to protect both sides since no single participant possesses the complete model. To address this, we propose RISE, a Robust model Intellectual property protection scheme using client-Server watermark Embedding for SFL. Specifically, RISE adopts an asymmetric client-server watermarking design: the server embeds feature-based watermarks through a loss regularization term, while clients embed backdoor-based watermarks by injecting predefined trigger samples into private datasets. This co-embedding strategy enables both clients and the server to verify model ownership. Experimental results on standard datasets and multiple network architectures show that RISE achieves over 95% watermark detection rate (p-value lt 0.03) across most settings. It exhibits no mutual interference between client- and server-side watermarks and remains robust against common removal attacks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 46 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

25 of 46 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  6. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 603
  7. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  8. 2018Distributed learning of deep neural network over multiple agentscited by 279
  9. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  10. 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 100
  11. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  12. 2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 69
13 more
  1. 2022Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentationcited by 42
  2. 2020WAFFLE: Watermarking in Federated Learningcited by 37
  3. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 36
  4. 2020Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluationscited by 31
  5. 2022FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Modelcited by 30
  6. 2023Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shiftscited by 28
  7. 2022Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooringcited by 17
  8. 2024A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learningcited by 17
  9. 2024Federated Graph Learning with Structure Proxy Alignmentcited by 14
  10. 2024ParallelSFL: A Novel Split Federated Learning Framework Tackling Heterogeneity Issuescited by 10
  11. 2024Federated Graph Learning for Cross-Domain Recommendationcited by 9
  12. 2025dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysiscited by 9
  13. 2023FedRight: An Effective Model Copyright Protection for Federated Learningcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Harmless Backdoor-based Client-side Watermarking in Federated Learning
  2. 2025Server-Enforced Watermarking in U-Shaped Split Federated Learning
  3. 2026Collaborative Threshold Watermarking
  4. 2025FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning
  5. 2024FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
  6. 2021Towards Practical Watermark for Deep Neural Networks in Federated Learning
  7. 2025Traceable Black-box Watermarks for Federated Learning
  8. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protection