paper-with-me

Papers

Robust Client-Server Watermarking for Split Federated Learning

2025-11-17 · Jiaxiong Tang, Zhengchunmin Dai, Liantao Wu, Peng Sun, Honglong Chen, Zhenfu Cao 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.

📄 PDF Abstract BibTeX arXiv:2511.13598

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Sigil: Server-Enforced Watermarking in U-Shaped Split Federated Learning via Gradient Injection

2025-11-18 · Zhengchunmin Dai, Jiaxiong Tang, Peng Sun, Honglong Chen 외 arxiv

In decentralized machine learning paradigms such as Split Federated Learning (SFL) and its variant U-shaped SFL, the server's capabilities are severely restricted. Although this enhances client-side privacy, it also leav…

Federated LearningAnomaly Detection

Collaborative Split Federated Learning with Parallel Training and Aggregation

2025-04-22 · Yiannis Papageorgiou, Yannis Thomas, Alexios Filippakopoulos, Ramin Khalili 외

Federated learning (FL) operates based on model exchanges between the server and the clients, and it suffers from significant client-side computation and communication burden. Split federated learning (SFL) arises a prom…

Federated Learning

WAFFLE: Watermarking in Federated Learning

2020-08-17 · Buse Gul Atli, Yuxi Xia, Samuel Marchal, N. Asokan

Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides. The training is coordinated via a central server which is, typi…

Federated Learning

Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring

2022-11-14 · Wenyuan Yang, Shuo Shao, Yue Yang, Xiyao Liu 외

Federated learning (FL) allows multiple participants to collaboratively build deep learning (DL) models without directly sharing data. Consequently, the issue of copyright protection in FL becomes important since unrelia…

Federated Learning

Communication and Storage Efficient Federated Split Learning

2023-02-11 · Yujia Mu, Cong Shen

Federated learning (FL) is a popular distributed machine learning (ML) paradigm, but is often limited by significant communication costs and edge device computation capabilities. Federated Split Learning (FSL) preserves …

Federated Learning