Privacy-Preserving Machine Learning: A use-case-driven approach to building and protecting ML pipelines from privacy and security threats

Gain hands-on experience in data privacy and privacy-preserving machine learning with open-source ML frameworks, while exploring techniques and algorithms to protect sensitive data from privacy breaches

• Understand machine learning privacy risks and employ machine learning algorithms to safeguard data against breaches
• Develop and deploy privacy-preserving ML pipelines using open-source frameworks
• Gain insights into confidential computing and its role in countering memory-based data attacks
• Purchase of the print or Kindle book includes a free PDF eBook

Privacy regulations are evolving each year and compliance with privacy regulations is mandatory for every enterprise. Machine learning engineers are required to not only analyze large amounts of data to gain crucial insights, but also comply with privacy regulations to protect sensitive data. This may seem quite challenging considering the large volume of data involved and lack of in-depth expertise in privacy-preserving machine learning.

This book delves into data privacy, machine learning privacy threats, and real-world cases of privacy-preserving machine learning, as well as open-source frameworks for implementation. You'll be guided through developing anti-money laundering solutions via federated learning and differential privacy. Dedicated sections also address data in-memory attacks and strategies for safeguarding data and ML models. The book concludes by discussing the necessity of confidential computation, privacy-preserving machine learning benchmarks, and cutting-edge research.

By the end of this machine learning book, you'll be well-versed in privacy-preserving machine learning and know how to effectively protect data from threats and attacks in the real world.

• Study data privacy, threats, and attacks across different machine learning phases
• Explore Uber and Apple cases for applying differential privacy and enhancing data security
• Discover IID and non-IID data sets as well as data categories
• Use open-source tools for federated learning (FL) and explore FL algorithms and benchmarks
• Understand secure multiparty computation with PSI for large data
• Get up to speed with confidential computation and find out how it helps data in memory attacks

This book is for data scientists, machine learning engineers, and privacy engineers who have working knowledge of mathematics as well as basic knowledge in any one of the ML frameworks (TensorFlow, PyTorch, or scikit-learn).

1. Introduction to Data Privacy, Privacy threats and breaches
2. Machine Learning Phases and privacy threats/attacks in each phase
3. Overview of Privacy Preserving Data Analysis and Introduction to Differential Privacy
4. Differential Privacy Algorithms, Pros and Cons
5. Developing Applications with Different Privacy using open source frameworks
6. Need for Federated Learning and implementing Federated Learning using open source frameworks
7. Federated Learning benchmarks, startups and next opportunity
8. Homomorphic Encryption and Secure Multiparty Computation
9. Confidential computing - what, why and current state
10. Privacy Preserving in Large Language Models