FedAWM: Adaptive watermark allocation in non-IID federated learning
文献类型：期刊论文
| 作者 | Sun, Jiahao1,2; Yang, Xiaodong1,2; Chen, Shubai1,2; Qin, Xin1,2; Zeng, Bixiao1,2 |
| 刊名 | KNOWLEDGE-BASED SYSTEMS
 |
| 出版日期 | 2026-01-15 |
| 卷号 | 332页码:12 |
| 关键词 | Federated learning Black-box watermark Non-independent and identically distributed (non-IID) Adaptive watermark allocation |
| ISSN号 | 0950-7051 |
| DOI | 10.1016/j.knosys.2025.114938 |
| 英文摘要 | Black-box watermark is a widely adopted solution for protecting model copyrights in Federated Learning (FL), where additional watermark tasks are trained concurrently with the main tasks. However, a conflict between the gradients of the main and watermark tasks can lead to performance degradation, hindered convergence, and low watermark fidelity. This issue is further complicated by the non-independent and identically distributed (non-IID) data among FL clients, as the effectiveness of watermarking also varies across them if watermarks are injected uniformly. Inspired by the ability of black-box watermarks to be shared through FL aggregation, we proposed a novel method called Adaptive Watermark Allocation in non-IID Federated Learning (FedAWM) to optimize both main and watermark tasks. Instead of assigning watermark tasks uniformly, FedAWM evaluates each client's ability to accommodate watermark training and adjusts the embedding strength accordingly. The server periodically assesses clients' watermark performance and then allocates watermark samples proportionally and asymmetrically, prioritizing clients with a higher tolerance to task interference. This process ensures that capable clients embed stronger watermarks, while others receive reduced or no watermark assignments. Extensive experiments on four benchmark datasets demonstrate that FedAWM achieves high main-task accuracy and watermark detection fidelity, while also maintaining robustness under various attacks, including model extraction, distillation, and adversarial manipulations. |
| 资助项目 | National Natural Science Foundation of China[62202455] ; National Natural Science Foundation of China[62402476] ; Beijing Natural Science Foundation[L241027] ; Beijing Natural Science Foundation[L22100] ; Innovation Funding of ICT, CAS[E561060] ; Innovation Funding of ICT, CAS[E563100] ; China Postdoctoral Science Foundation[2024M753296] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001631857700002 |
| 出版者 | ELSEVIER |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42987]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Yang, Xiaodong |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Sun, Jiahao,Yang, Xiaodong,Chen, Shubai,et al. FedAWM: Adaptive watermark allocation in non-IID federated learning[J]. KNOWLEDGE-BASED SYSTEMS,2026,332:12. |
| APA | Sun, Jiahao,Yang, Xiaodong,Chen, Shubai,Qin, Xin,&Zeng, Bixiao.(2026).FedAWM: Adaptive watermark allocation in non-IID federated learning.KNOWLEDGE-BASED SYSTEMS,332,12. |
| MLA | Sun, Jiahao,et al."FedAWM: Adaptive watermark allocation in non-IID federated learning".KNOWLEDGE-BASED SYSTEMS 332(2026):12. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。