3 Differential privacy for machine learning (Part-2)
This chapter covers
- Design principles of differentially private machine learning algorithms
- Designing and implementing differentially private supervised learning algorithms (e.g., Naive Bayes classification, logistic regression, and linear regression)
- Designing and implementing differentially private unsupervised learning algorithms (e.g., K-means clustering)
- Working with a case study on “Differentially Private Principal Component Analysis” to walk you through the process of designing and analyzing a differentially private machine learning algorithm
In the previous chapter, we investigated the definition and general usage of differential privacy and the properties of differential privacy that work under different scenarios (e.g., post-processing property, group property, and composition properties). We also looked into common and widely adopted differentially private mechanisms that have served as essential building blocks in various privacy-preserving algorithms and applications. This chapter will walk through how to use those building blocks to design and implement multiple differentially private machine learning algorithms and how to apply such algorithms in real-world scenarios. This will be our second part of differential privacy for machine learning.
