用可学习加密+ViT实现医疗图像安全共享，兼顾隐私与性能
ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification
- 基于块像素操作的可学习加密，每密钥生成唯一混淆模式
- 集成ViT后在加密数据上保持高分类准确率，抗比特攻击与最小差异攻击
- 适合需要高安全性的医疗数据共享场景，如跨机构影像分析
隐私保护与安全的数据共享对医学图像分析至关重要，同时保持精度并降低计算开销也极为关键。将现有深度神经网络（DNN）应用于加密医学数据往往困难，且常导致性能与安全性的妥协。为此，本研究提出一种安全框架：基于块像素操作的可学习加密方法用于数据加密，并与视觉变压器（ViT）集成。该框架通过每密钥生成独特混淆模式，确保数据隐私与安全，对主流比特攻击和最小差异攻击具有强鲁棒性，同时保持较高分类性能。
原文摘要 · Abstract (English)
Privacy-preserving and secure data sharing are critical for medical image analysis while maintaining accuracy and minimizing computational overhead are also crucial. Applying existing deep neural networks (DNNs) to encrypted medical data is not always easy and often compromises performance and security. To address these limitations, this research introduces a secure framework consisting of a learnable encryption method based on the block-pixel operation to encrypt the data and subsequently integrate it with the Vision Transformer (ViT). The proposed framework ensures data privacy and security by creating unique scrambling patterns per key, providing robust performance against leading bit attacks and minimum difference attacks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。