Scholarlink

<p>The rapid growth in generative models for medical imaging demands robust methodologies for preserving patient privacy and ensuring that the synthetic data remains authentic. The leaking of identifiable patterns from real clinical data into generated images presents serious difficulties in terms of regulatory compliance, ethical deployment, and clinical trust. This work, therefore, attempts to identify the actual clinical images mistakenly included in a generative adversarial network during its training and enables privacy-preserving generative modeling. A hybrid Siamese architecture consisting of ResNet-50 and vision transformer backbones is introduced to learn robust feature representations. Cross-attention is incorporated into the model for multiscale feature fusion, and an adaptive similarity metric is developed to improve discriminative comparison of paired images. We use a hybrid loss function that combines an angular term and a binary cross-entropy term during training for stable optimization. Through extensive evaluation on lung CT scan datasets, we show that our model has shown the highest average accuracy (<InlineEquation ID="IEq1"><EquationSource Format="TEX">\(0.883 \pm 0.03\)</EquationSource></InlineEquation>) and an equally good F1-score (<InlineEquation ID="IEq2"><EquationSource Format="TEX">\(0.540 \pm 0.06\)</EquationSource></InlineEquation>) This is a reasonable classification performance and also points out the difficulties involved in the detection of generative fingerprints. These findings support the superior discriminative power of the model for subtle generative ’fingerprints’. With a presented novel privacy-preserving framework for generative model validation, the proposed method can be a contribution to the development of secure and ethical validation for clinical AI systems.</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

Hybrid siamese architecture for detecting genuine training data fingerprints in medical generative adversarial networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月26日

查看全文
  • Lekshmi Kalinathan,
  • Farhaan Areeb,
  • K. Devi,
  • Divyansh Vashist

摘要

The rapid growth in generative models for medical imaging demands robust methodologies for preserving patient privacy and ensuring that the synthetic data remains authentic. The leaking of identifiable patterns from real clinical data into generated images presents serious difficulties in terms of regulatory compliance, ethical deployment, and clinical trust. This work, therefore, attempts to identify the actual clinical images mistakenly included in a generative adversarial network during its training and enables privacy-preserving generative modeling. A hybrid Siamese architecture consisting of ResNet-50 and vision transformer backbones is introduced to learn robust feature representations. Cross-attention is incorporated into the model for multiscale feature fusion, and an adaptive similarity metric is developed to improve discriminative comparison of paired images. We use a hybrid loss function that combines an angular term and a binary cross-entropy term during training for stable optimization. Through extensive evaluation on lung CT scan datasets, we show that our model has shown the highest average accuracy (\(0.883 \pm 0.03\)) and an equally good F1-score (\(0.540 \pm 0.06\)) This is a reasonable classification performance and also points out the difficulties involved in the detection of generative fingerprints. These findings support the superior discriminative power of the model for subtle generative ’fingerprints’. With a presented novel privacy-preserving framework for generative model validation, the proposed method can be a contribution to the development of secure and ethical validation for clinical AI systems.