霍恩斯-CNN模型:一个节能,完全同型的残留数系统卷积神经网络模型,用于隐私保护的阅读障碍神经生物标志物的分类
Opeyemi Lateef Usman1,2, Ravie Chandren Muniyandi3, Khairuddin Omar4
1Research Centre for Cyber Security, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), 43600, Bangi, Selangor, Malaysia. usmanol@tasued.edu.ng.
Brain informatics
|April 30, 2025
概括
这项研究介绍了HoRNS-CNN,这是一种用于对神经成像数据进行安全,保护隐私的分析的新型模型. 它使用云中的加密数据有效地识别神经发育障碍的神经生物标志物.
科学领域:
- 神经科学是一个神经科学.
- 计算机科学 计算机科学
- 医疗成像医学成像
背景情况:
- 基于云的机器学习 (ML) 能够从神经成像数据远程识别神经发育障碍的神经生物标志物.
- 由于神经成像数据集的敏感性,安全的深度学习 (DL) 算法至关重要.
- 现有的完全同型加密 (FHE) 深卷积神经网络 (CNN) 模型的准确性低,延迟高,效率低下.
研究的目的:
- 引入HoRNS-CNN模型,以对加密的神经成像数据进行高效,保护隐私的预测.
- 解决当前FHE-CNN模型的局限性,包括精度,延迟和计算开销.
- 证明拟议模型的能源效率和同型性.
主要方法:
- 将残留数系统FHE (RNS-FHE) 方案与预先训练的深度CNN模型集成,用于基于云的分析.
- FPGA实现了RNS-FHE方案,嵌入了8位灰度像素加密的同态编码器/解码器电路.
- 使用泰勒多项式近似和批量规范化进行高精度同态计算,调整 ReLU 激活函数.
主要成果:
- 霍恩斯-CNN模型有效地管理了加密图像扩展,并提高了非对称的复杂性.
- 与现有的FHE-CNN模型相比,表现出更高的性能和更快的特征提取.
- 在一小时内实现了40万个神经生物标记特征的高效预测.
结论:
- 霍恩斯-CNN为神经成像数据的隐私保护分析提供了有效的解决方案.
- 该模型提高了识别神经发育障碍神经生物标志物的安全性和效率.
- HoRNS-CNN代表了安全的基于云的医疗应用深度学习的重大进步.
相关概念视频
Learning Disabilities
64
Learning disabilities are cognitive disorders caused by neurological impairments that affect cognitive functions like language and reading, without indicating overall intellectual or developmental challenges. These disabilities differ from global intellectual or developmental disabilities as they are limited to distinct cognitive functions. Common learning disabilities include dysgraphia, dyslexia, and dyscalculia, each of which impacts unique aspects of learning.
Dyslexia
Dyslexia is a...
Dyslexia
Dyslexia is a...
64
Language and Cognition
287
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
287


