Privacy-Preserving Machine Learning
Год издания: 2023
Автор: Chang J.M., Zhuang D., Samaraweera D.
Издательство: Manning
ISBN: 978-1617298042
Язык: Английский
Формат: PDF
Качество: Издательский макет или текст (eBook)
Интерактивное оглавление: Да
Количество страниц: 335
Описание: Keep sensitive user data safe and secure without sacrificing the performance and accuracy of your Machine Learning models.
In Privacy Preserving Machine Learning, you will learn:
- Privacy considerations in machine learning
- Differential privacy techniques for machine learning
- Privacy-preserving synthetic data generation
- Privacy-enhancing technologies for data mining and database applications
- Compressive privacy for machine learning
Privacy Preserving Machine Learning is a comprehensive guide to avoiding data breaches in your Machine Learning projects. You’ll get to grips with modern privacy-enhancing techniques such as differential privacy, compressive privacy, and synthetic data generation. Based on years of DARPA-funded cybersecurity research, ML engineers of all skill levels will benefit from incorporating these privacy-preserving practices into their model development. By the time you’re done reading, you’ll be able to create Machine Learning systems that preserve user privacy without sacrificing data quality and model performance.
Оглавление
PART 1 BASICS OF PRIVACY-PRESERVING MACHINE LEARNING WITH DIFFERENTIAL PRIVACY 1
1. Privacy considerations in machine learning 3
2. Differential privacy for machine learning 25
3. Advanced concepts of differential privacy for machine learning 56
PART 2 LOCAL DIFFERENTIAL PRIVACY AND SYNTHETIC DATA GENERATION 93
4. Local differential privacy for machine learning 95
5. Advanced LDP mechanisms for machine learning 123
6. Privacy-preserving synthetic data generation 146
PART 3 BUILDING PRIVACY-ASSURED MACHINE LEARNING APPLICATIONS 177
7. Privacy-preserving data mining techniques 179
8. Privacy-preserving data management and operations 202
9. Compressive privacy for machine learning 233
10. Putting it all together: Designing a privacy-enhanced platform (DataHub) 268
