Privacy-Preserving Logistic Regression
نویسنده
چکیده
Logistic regression is an important statistical analysis methods widely used in research fields, including health, business and government. On the other hand preserving data privacy is a crucial aspect in every information system. Many privacy-preserving protocols have been proposed for different statistical techniques, with various data distributions, owners and users. In this paper, we propose a new method to securely compute logistic regression of data, privately shared among two or more data owners. Using this secure protocol, data users can receive the coefficient vector of logistic regression from the data owners, who jointly execute a privacy-preserving protocol, in which only encrypted values are exchanged between them. At the end of the protocol, each data owner will send her portion of the final results to the user to construct the final query result. We have tested our method along with the secure building blocks using sample data to illustrate the performance of the results in terms of computational and communication complexities.
منابع مشابه
Privacy-preserving logistic regression
This paper addresses the important tradeoff between privacy and learnability, when designing algorithms for learning from private databases. We focus on privacy-preserving logistic regression. First we apply an idea of Dwork et al. [6] to design a privacy-preserving logistic regression algorithm. This involves bounding the sensitivity of regularized logistic regression, and perturbing the learn...
متن کاملPrivLogit: Efficient Privacy-preserving Logistic Regression by Tailoring Numerical Optimizers
Safeguarding privacy in machine learning is highly desirable, especially in collaborative studies across many organizations. Privacy-preserving distributed machine learning (based on cryptography) is popular to solve the problem. However, existing cryptographic protocols still incur excess computational overhead. Here, we make a novel observation that this is partially due to naive adoption of ...
متن کاملPrivacy-Preserving Maximum Likelihood Estimation for Distributed Data
Recent technological advances enable the collection of huge amounts of data. Commonly, these data are generated, stored, and owned by multiple entities that are unwilling to cede control of their data. This distributed environment requires statistical tools that can produce correct results while preserving data privacy. Privacy-preserving protocols have been proposed to solve specific statistic...
متن کاملDifferentially Private Empirical Risk Minimization
Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the ε-differential privacy definition du...
متن کاملPreserving Privacy in Data Mining using hybrid of Auto-Associative Neural Network and Particle Swarm Optimization: An application for bankruptcy prediction in banks
Data mining has emerged as a significant technology for gaining knowledge from vast quantities of business data, financial data, networked data and medical data. The goal of data mining is approaches are to develop generalized knowledge rather than identify specific information against specific individual. There has been growing concern that use of this technology is violating individual privac...
متن کامل