An Efficient Solution for Privacy-preserving Naïve Bayes Classification in Fully Distributed Data Model
نویسندگان
چکیده
Abstract—Recently, privacy preservation has become one of the most important problems in data mining and machine learning. In this paper, we propose a novel privacy-preserving Naïve Bayes classifier for fully distributed scenario where each record is only kept by unique owner. Our proposed solution based on secure multi-party computation protocol, so that it capability to securely protect owner’s privacy, as well accurately guarantee classification model. Furthermore, our experimental results show new efficient enough practical applications. Tóm tắt—Gần đây, bảo vệ tính riêng tư đã trở thành một trong những vấn đề quan trọng nhất khai phá dữ liệu và học máy. Trong bài báo này, chúng tôi xuất bộ phân lớp đảm mới cho kịch bản tán đầy đủ đó mỗi ghi chỉ được giữ bởi người sở hữu duy nhất. Giải pháp nhóm tác giả dựa trên toán mật nhiều viên nên nó có khả năng an toàn sự của cũng như chính xác mô hình lớp. Hơn thế nữa, các kết quả thực nghiệm ra rằng giải hiệu ứng dụng tế.
منابع مشابه
Privacy Preserving Naïve Bayes Classifier for Vertically Partitioned Data
Privacy-Preserving Data Mining – developing models without seeing the data – is receiving growing attention. This paper assumes a privacy-preserving distributed data mining scenario: data sources collaborate to develop a global model, but must not disclose their data to others. Näıve Bayes is often used as a baseline classifier, consistently providing reasonable classification performance. This...
متن کاملPrivacy-preserving naive Bayes classification on distributed data via semi-trusted mixers
Distributed data mining applications, such as those dealing with health care, finance, counter-terrorism and homeland defense, use sensitive data from distributed databases held by different parties. This comes into direct conflict with an individual’s need and right to privacy. It is thus of great importance to develop adequate security techniques In this paper, we consider privacy-preserving ...
متن کاملPrivacy-Preserving Publish/Subscribe: Efficient Protocols in a Distributed Model
We consider the problem of modeling and designing efficient and privacy-preserving publish/subscribe protocols in a distributed model where parties can act as publishers or subscribers or both, and there are no brokers or other types of parties. The problem is particularly challenging as privacy demands on such protocols come with efficiency limitations; most notably, the publisher must send me...
متن کاملMacro for Naïve Bayes Classification
The supervised classification also known as pattern recognition, discrimination, or supervised learning consists of assigning new cases to one of a set of pre-defined classes given a sample of cases for which the true classes are known. The Naïve Bayes (NB) technique of supervised classification has become increasingly popular in the recent years. Despite its unrealistic assumption that feature...
متن کاملDistributed Privacy Preserving Data Collection
We study the distributed privacy preserving data collection problem: an untrusted data collector (e.g., a medical research institute) wishes to collect data (e.g., medical records) from a group of respondents (e.g., patients). Each respondent owns a multi-attributed record which contains both non-sensitive (e.g., quasi-identifiers) and sensitive information (e.g., a particular disease), and sub...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Nghiên c?u khoa h?c và công ngh? trong l?nh v?c an toàn thông tin
سال: 2022
ISSN: ['2615-9570']
DOI: https://doi.org/10.54654/isj.v1i15.840