An interesting and well structured book about an emerging discipline that will certainly keep growing in importance.
Keep sensitive user data safe and secure, without sacrificing the accuracy of your machine learning models.
In
Privacy Preserving Machine Learning, you will learn:
- Differential privacy techniques and their application in supervised learning
- Privacy for frequency or mean estimation, Naive Bayes classifier, and deep learning
- Designing and applying compressive privacy for machine learning
- Privacy-preserving synthetic data generation approaches
- Privacy-enhancing technologies for data mining and database applications
Privacy Preserving Machine Learning is a comprehensive introduction to data privacy in machine learning. Based on years of DARPA-funded cybersecurity research, the book is filled with lightbulb moments that will change the way you think about algorithm design. You’ll learn how to apply privacy-enhancing techniques to common machine learning tasks, and experiment with source code fresh from the latest academic papers.