Noise Addition Based Approach for Privacy Preserving Data Stream Classification

Abstract

The research sector is paying close attention to data stream mining, which has many uses in fields including banking, education, networking, telecommunication, weather forecasting, stock market, and more, as a result of the significant increase of massive data streams. As a result, researchers are paying increasing attention to protecting privacy in data stream mining. In this work, we provide a noise addition-based method for data stream privacy-preserving classification that applies classification algorithms to large data streams while maintaining data privacy. This fascinating field of study has recently gained additional insight from the developing big data analytics context.