@inproceedings{xu-etal-2025-enhancing-model,
    title = "Enhancing Model Privacy in Federated Learning with Random Masking and Quantization",
    author = "Xu, Zhibo  and
      JianHao, Zhu  and
      Xu, Jingwen  and
      Lv, Changze  and
      Wang, Zhenghua  and
      Huang, Zisu  and
      Wang, Xiaohua  and
      Wu, Muling  and
      Qian, Qi  and
      Zheng, Xiaoqing  and
      Huang, Xuanjing",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.632/",
    doi = "10.18653/v1/2025.findings-emnlp.632",
    pages = "11804--11816",
    ISBN = "979-8-89176-335-7",
    abstract = "The primary goal of traditional federated learning is to protect data privacy by enabling distributed edge devices to collaboratively train a shared global model while keeping raw data decentralized at local clients. The rise of large language models (LLMs) has introduced new challenges in distributed systems, as their substantial computational requirements and the need for specialized expertise raise critical concerns about protecting intellectual property (IP). This highlights the need for a federated learning approach that can safeguard both sensitive data and proprietary models. To tackle this challenge, we propose FedQSN, a federated learning approach that leverages random masking to obscure a subnetwork of model parameters and applies quantization to the remaining parameters. Consequently, the server transmits only a privacy-preserving proxy of the global model to clients during each communication round, thus enhancing the model{'}s confidentiality. Experimental results across various models and tasks demonstrate that our approach not only maintains strong model performance in federated learning settings but also achieves enhanced protection of model parameters compared to baseline methods."
}