.png){kind=icon}
返回
Privacy-preserving multi-party logistic regression in cloud computing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csi.2024.103857.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, machine learning techniques have been widely deployed in various fields. However, machine learning faces problems like high computation overhead, low training accuracy, and poor security due to data silos, privacy issues and communication limitations, especially in the environment of cloud computing. Logistic regression (LR) is a popular machine learning method used for prediction, while current LR algorithms suffer from high computation cost and communication burden due to interactions between users and cloud servers. In this paper, we propose a Privacy-Preserving Multi-party Logistic Regression (PPMLR) algorithm, which achieves privacy-preserving and non-interactive gradient descent regression training in machine learning. PPMLR uses the Distributed two Trapdoors Public-Key Cryptosystem (DT-PKC) as a main building block, which satisfies additive homomorphic encryption. Specifically, users go off-line after encrypting local private data, then the service provider (SP) trains the global logistic regression model by interacting with the cloud server (CS), so that the confidentiality and privacy of user's private data can be guaranteed during the training process. We prove by detailed security proof that PPMLR guarantees data and model privacy. Finally, we conduct experiments on two popular medical datasets from the UCI machine learning repository. The experimental results show that PPMLR can conduct privacy-preserving training efficiently. Comparison with the stat-of-theart Privacy-Preserving Logistic Regression Algorithm (PPLRA) shows that the model training time is reduced by about 4 times.
Keyword:
Machine learning
Cloud computing
Logistic regression
Privacy-preserving
Homomorphic encryption
期刊
C
IF:
3.1
论文数:
2.3K
被引数:
2.0K
机构
引用论文
分享收藏Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Development of Continuous Surfactin Production from Potato Process Effluent by Bacillus subtilis in an Airlift Reactor通过芽孢杆菌在气升式反应器中从马铃薯加工废水中连续生产表面活性素的发展
PREAI
分享收藏
查看更多内容