Машинное обучение с сохранением конфиденциальности Дж. Чанг

Privacy-Preserving Machine Learning

Keep sensitive user data safe and secure, without sacrificing theaccuracy of your machine learning models.In Privacy Preserving Machine Learning, you will learn:Differential privacy techniques and their application insupervised learningPrivacy for frequency or mean estimation, Naive Bayes classifier,and deep learningDesigning and applying compressive privacy for machine learningPrivacy-preserving synthetic data generation approachesPrivacy-enhancing technologies for data mining and database applicationsPrivacy Preserving Machine Learning is a comprehensive guide to avoiding data breaches in your machine learning projects. Youll 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 and seniorities will benefit from incorporating these privacy-preserving practices into their model development.

• Autor: J. Chang, G. Samaraweera
• Wydawnictwo: Manning Publications
• Rok wydania: 2023
• Okładka: miękka
• Liczba stron: 300
• Wymiary: 18.7 x 23.6 x 2.1 cm
• Język: angielski
• ISBN: 9781617298042