Aravilli Privacy-Preserving Machine Learning

A use-case-driven approach to building and protecting ML pipelines from privacy and security threats
1. Auflage 2024
ISBN: 978-1-80056-422-0
Verlag: De Gruyter
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 402 Seiten

- In an era of evolving privacy regulations, compliance is mandatory for every enterprise

- Machine learning engineers face the dual challenge of analyzing vast amounts of data for insights while protecting sensitive information

- This book addresses the complexities arising from large data volumes and the scarcity of in-depth privacy-preserving machine learning expertise, and covers a comprehensive range of topics from data privacy and machine learning privacy threats to real-world privacy-preserving cases

- As you progress, you'll be guided through developing anti-money laundering solutions using federated learning and differential privacy

- Dedicated sections will explore data in-memory attacks and strategies for safeguarding data and ML models

- You'll also explore the imperative nature of confidential computation and privacy-preserving machine learning benchmarks, as well as frontier research in the field

- Upon completion, you'll possess a thorough understanding of privacy-preserving machine learning, equipping them to effectively shield data from real-world threats and attacks

Autoren/Hrsg.

Aravilli, Srinivasa Rao

Weitere Mitwirkende

Hamilton, Sam

Fachgebiete

• Technische Wissenschaften Technik Allgemein Technik: Allgemeines
• Interdisziplinäres Wissenschaften Wissenschaften Interdisziplinär Naturwissenschaften, Technik, Medizin
• Mathematik | Informatik EDV | Informatik Technische Informatik Computersicherheit Datensicherheit, Datenschutz

Inhaltsverzeichnis

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

Über Autor(innen)

Aravilli Srinivasa Rao :

Srinivasa Rao Aravilli boasts 27 years of extensive experience in technology, research, and leadership roles, spearheading innovation in various domains such as Information Retrieval, Search, ML/AI, Distributed Computing, Network Analytics, Privacy, and Security. Currently working as a Senior Director of Machine Learning Engineering at Capital One, Bangalore, he has a proven track record of driving new products from conception to outstanding customer success. Prior to his tenure at Capital One, Srinivasa held prominent leadership positions at Visa, Cisco, and Hewlett Packard, where he led product groups focused on data privacy, machine learning, and Generative AI. He holds a Master's Degree in Computer Applications from Andhra University, Visakhapatnam, India.