Evaluating Optimal Differentially Private Learning - Shallow and Deep Techniques

Abstract

Data analytics is an evolving arena in today’s technological evolution. Big data, IoT and machine learning are multidisciplinary fields which pave way for large scale data analytics. Data is the basic ingredient in all type of analytical tasks, which is collected from various sources through online activity. Data divulged in these day-to-day activities contain personal information of individuals. These sensitive details may be disclosed when data is shared with data analysts or researchers for futuristic analysis. In order to respect the privacy of individuals involved, it is required to protect data to avoid any intentional harm. Differential privacy is an algorithm that allows controlled machine learning practices for quality analytics. With differential privacy, the outcome of any analytical task is unaffected by the presence or absence of a single individual or small group of individuals. But, it goes without saying that privacy protection diminishes the usefulness of data for analysis. Hence privacy preserving analytics requires algorithmic techniques that can handle privacy, data quality and efficiency simultaneously. Since one cannot be obtained without degrading the other, an optimal solution that balances the attributes is considered acceptable. The work in this paper, proposes different optimization techniques for shallow and deep learners. While evolutionary approach is proposed for shallow learning, private deep learning is optimized using Bayesian method. The results prove that the Bayesian optimized private deep learning model gives a quantifiable trade-off between the privacy, utility and performance