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

by: Srinivasa Rao Aravilli (Author)

Publisher: Packt Publishing

Publication Date: May 24, 2024

Language: English

Print Length: 402 pages

ISBN-10: 1800564678

ISBN-13: 9781800564671

Book Description

Gain hands-on experience in data privacy and privacy-preserving machine leaing with open-source ML frameworks, while exploring techniques and algorithms to protect sensitive data from privacy breaches Key FeaturesUnderstand machine leaing privacy risks and employ machine leaing algorithms to safeguard data against breachesDevelop and deploy privacy-preserving ML pipelines using open-source frameworksGain insights into confidential computing and its role in countering memory-based data attacksPurchase of the print or Kindle book includes a free PDF eBookBook DescriptionPrivacy regulations are evolving each year and compliance with privacy regulations is mandatory for every enterprise. Machine leaing 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 leaing.This book delves into data privacy, machine leaing privacy threats, and real-world cases of privacy-preserving machine leaing, as well as open-source frameworks for implementation. You'll be guided through developing anti-money laundering solutions via federated leaing 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 leaing benchmarks, and cutting-edge research.By the end of this machine leaing book, you'll be well-versed in privacy-preserving machine leaing and know how to effectively protect data from threats and attacks in the real world.What you will leaStudy data privacy, threats, and attacks across different machine leaing phasesExplore Uber and Apple cases for applying differential privacy and enhancing data securityDiscover IID and non-IID data sets as well as data categoriesUse open-source tools for federated leaing (FL) and explore FL algorithms and benchmarksUnderstand secure multiparty computation with PSI for large dataGet up to speed with confidential computation and find out how it helps data in memory attacksWho this book is forThis book is for data scientists, machine leaing 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-lea).Table of ContentsIntroduction to Data Privacy, Privacy threats and breachesMachine Leaing Phases and privacy threats/attacks in each phaseOverview of Privacy Preserving Data Analysis and Introduction to Differential PrivacyDifferential Privacy Algorithms, Pros and ConsDeveloping Applications with Different Privacy using open source frameworksNeed for Federated Leaing and implementing Federated Leaing using open source frameworksFederated Leaing benchmarks, startups and next opportunityHomomorphic Encryption and Secure Multiparty ComputationConfidential computing - what, why and current statePrivacy Preserving in Large Language Models
About the Author
Gain hands-on experience in data privacy and privacy-preserving machine leaing with open-source ML frameworks, while exploring techniques and algorithms to protect sensitive data from privacy breaches Key FeaturesUnderstand machine leaing privacy risks and employ machine leaing algorithms to safeguard data against breachesDevelop and deploy privacy-preserving ML pipelines using open-source frameworksGain insights into confidential computing and its role in countering memory-based data attacksPurchase of the print or Kindle book includes a free PDF eBookBook DescriptionPrivacy regulations are evolving each year and compliance with privacy regulations is mandatory for every enterprise. Machine leaing 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 leaing.This book delves into data privacy, machine leaing privacy threats, and real-world cases of privacy-preserving machine leaing, as well as open-source frameworks for implementation. You'll be guided through developing anti-money laundering solutions via federated leaing 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 leaing benchmarks, and cutting-edge research.By the end of this machine leaing book, you'll be well-versed in privacy-preserving machine leaing and know how to effectively protect data from threats and attacks in the real world.What you will leaStudy data privacy, threats, and attacks across different machine leaing phasesExplore Uber and Apple cases for applying differential privacy and enhancing data securityDiscover IID and non-IID data sets as well as data categoriesUse open-source tools for federated leaing (FL) and explore FL algorithms and benchmarksUnderstand secure multiparty computation with PSI for large dataGet up to speed with confidential computation and find out how it helps data in memory attacksWho this book is forThis book is for data scientists, machine leaing 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-lea).Table of ContentsIntroduction to Data Privacy, Privacy threats and breachesMachine Leaing Phases and privacy threats/attacks in each phaseOverview of Privacy Preserving Data Analysis and Introduction to Differential PrivacyDifferential Privacy Algorithms, Pros and ConsDeveloping Applications with Different Privacy using open source frameworksNeed for Federated Leaing and implementing Federated Leaing using open source frameworksFederated Leaing benchmarks, startups and next opportunityHomomorphic Encryption and Secure Multiparty ComputationConfidential computing - what, why and current statePrivacy Preserving in Large Language Models Read more