Scholarlink

<p>The deep integration of artificial intelligence with the Internet of Medical Things (IoMT) has accelerated the adoption of federated learning (FL) for medical image classification. However, the decentralized training pipeline exposes FL to poisoning threats at both the data and model-update levels, potentially compromising diagnostic reliability. To address this challenge, we propose FedGF, an end-to-end two-stage defense scheme that combines client-side Genetic Data Selection (GDS) with server-side Federated Unlearning (FU) enhanced by LOF-based anomaly detection. GDS optimizes local training subsets through a fitness function that jointly considers parameter similarity, validation accuracy, and category-bias penalty, thereby filtering potentially poisoned samples before local training. During aggregation, FU further identifies and removes anomalous client updates and performs similarity-aware robust weighting. Experiments on the COVID-19 Radiography Database and the Pneumonia Chest X-ray Dataset under label-flipping attacks demonstrate that FedGF consistently improves robustness and convergence stability compared with conventional aggregation defenses.</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

A federated learning-based dual-filtering solution to combat data poisoning attacks in medical image classification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月29日

查看全文
  • Pengzhan Zheng,
  • Yuping Zhou,
  • Xiaolong Yu,
  • Weiwen Wang,
  • Shengqie Liao

摘要

The deep integration of artificial intelligence with the Internet of Medical Things (IoMT) has accelerated the adoption of federated learning (FL) for medical image classification. However, the decentralized training pipeline exposes FL to poisoning threats at both the data and model-update levels, potentially compromising diagnostic reliability. To address this challenge, we propose FedGF, an end-to-end two-stage defense scheme that combines client-side Genetic Data Selection (GDS) with server-side Federated Unlearning (FU) enhanced by LOF-based anomaly detection. GDS optimizes local training subsets through a fitness function that jointly considers parameter similarity, validation accuracy, and category-bias penalty, thereby filtering potentially poisoned samples before local training. During aggregation, FU further identifies and removes anomalous client updates and performs similarity-aware robust weighting. Experiments on the COVID-19 Radiography Database and the Pneumonia Chest X-ray Dataset under label-flipping attacks demonstrate that FedGF consistently improves robustness and convergence stability compared with conventional aggregation defenses.