Scholarlink

The surge in wearable technology for health has advanced personalized Human Activity Recognition (HAR), yet introduces privacy concerns under EU regulations such as the GDPR, the AI Act and the European Health Data Space (EHDS). This paper examines fine-tuning approaches for self-supervised models on wearable data, using Differentially Private Stochastic Gradient Descent (DP-SGD) to balance privacy and utility. Using the PAMAP2 dataset and the HarNet10 model, we compare classifier head and full model fine-tuning. Our results show that tuning only the classifier head (4.83% of parameters) preserves higher accuracy and F1-scores while significantly reducing vulnerability to membership inference attacks compared to non-private baselines. This strategy provides a lightweight and regulation-compliant framework for privacy-preserving HAR on wearables.

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

Differentially Private Fine-Tuning of Self-Supervised Learning Models for Human Activity Recognition on Wearables

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Oktay Ozan Güner,
  • Sergio Consoli,
  • Vicenç Gómez,
  • Mario Ceresa

摘要

The surge in wearable technology for health has advanced personalized Human Activity Recognition (HAR), yet introduces privacy concerns under EU regulations such as the GDPR, the AI Act and the European Health Data Space (EHDS). This paper examines fine-tuning approaches for self-supervised models on wearable data, using Differentially Private Stochastic Gradient Descent (DP-SGD) to balance privacy and utility. Using the PAMAP2 dataset and the HarNet10 model, we compare classifier head and full model fine-tuning. Our results show that tuning only the classifier head (4.83% of parameters) preserves higher accuracy and F1-scores while significantly reducing vulnerability to membership inference attacks compared to non-private baselines. This strategy provides a lightweight and regulation-compliant framework for privacy-preserving HAR on wearables.