.png){kind=icon}
返回
Radial Basis Function Network with Differential Privacy
.png){kind=icon}
PRE
AI
DOI：10.1016/j.future.2021.09.013.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Differential privacy (DP) remains a potent solution to what is arguably the defining issue in machine learning: balancing user privacy with an ever-increasing need for data. Practitioners must respect privacy, especially in sensitive healthcare domains. DP strives towards this aim by adding noise to training data to occlude its origin and nature, and is ideal for multiple Neural Network (NN) types. This includes deep varieties that utilise multiple hidden layers, and shallow ones with single hidden layers such as the Radial Base Function Network (RBFN). The work herein explores DP within this context by devising a model that leverages Gaussian RBF parameters to add privacy during training. Our model's efficacy is examined against two real and three synthetic datasets, with results showing reasonable trade-offs between accuracy and privacy. With high intra-class variation, we retained 100% accuracy for two synthetic datasets and a drop of only 1.72% for another. If privacy is prioritised with low intra-class variation, we achieved accuracy drops of 8%-23% with an inherited epsilon that never exceeds one, indicating a good privacy guarantee. We also show that timely training is achievable on a high-dimensional dataset consisting of 2M records and 170 features. (C) 2021 Elsevier B.V. All rights reserved.
Keyword:
Machine Learning
Differential Privacy
Radial Basis Function Network
RBFN
Distributed Training
Ensemble Learning
期刊
F
IF:
6.1
论文数:
6.9K
被引数:
2.3W
机构
引用论文
Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption基于同态加密的隐私保护逻辑回归集成方法.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏A Compressive Sensing-Based Automatic Sleep-Stage Classification System With Radial Basis Function Neural Network基于径向基函数神经网络的压缩感知睡眠阶段自动分类系统IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容