Scholarlink

<p>Federated edge learning (FEL) emerges as a novel distributed learning paradigm where multiple clients can jointly train a global model without collecting raw data. However, since adversaries can infer sensitive information from the global model and local updates, FEL remains vulnerable to various security challenges in the Internet of Things (IoT). In this paper, we consider three main challenges during the iterative training process: (1) how to ensure the confidentiality of the global model and local updates; (2) how to verify the integrity of local updates uploaded by clients with limited computational power; (3) how to verify the correctness of the aggregation result returned by the compromised server. To address the above challenges, we propose PDTV-FEL, a privacy-preserving and dual traceable verification federated learning scheme. Specifically, we first design a masked MK-CKKS approach that guarantees the confidentiality of the global model and local updates without incurring significant costs. Moreover, we adopt the BLS signature and double trapdoor chameleon hash function for secure traceable verification. The method not only ensures the integrity of local updates and the aggregation result but also enables identifying the wrong phase and epoch in case of incorrect results. Extensive evaluations on various datasets show the efficient verification of PDTV-FEL in comparison to other schemes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PDTV-FEL: privacy-preserving and dual traceable verification federated edge learning

  • 期刊论文

  • 发表日期：

    2026年5月19日

查看全文
  • Pan Zhang,
  • Lei Xu,
  • Chungen Xu,
  • Lin Mei,
  • Yaqing Ni

摘要

Federated edge learning (FEL) emerges as a novel distributed learning paradigm where multiple clients can jointly train a global model without collecting raw data. However, since adversaries can infer sensitive information from the global model and local updates, FEL remains vulnerable to various security challenges in the Internet of Things (IoT). In this paper, we consider three main challenges during the iterative training process: (1) how to ensure the confidentiality of the global model and local updates; (2) how to verify the integrity of local updates uploaded by clients with limited computational power; (3) how to verify the correctness of the aggregation result returned by the compromised server. To address the above challenges, we propose PDTV-FEL, a privacy-preserving and dual traceable verification federated learning scheme. Specifically, we first design a masked MK-CKKS approach that guarantees the confidentiality of the global model and local updates without incurring significant costs. Moreover, we adopt the BLS signature and double trapdoor chameleon hash function for secure traceable verification. The method not only ensures the integrity of local updates and the aggregation result but also enables identifying the wrong phase and epoch in case of incorrect results. Extensive evaluations on various datasets show the efficient verification of PDTV-FEL in comparison to other schemes.