
As an Amazon Associate and affiliate partner, Menrva Books earns from qualifying purchases. Learn more
This book provides a thorough overview of the evolution of privacy-preserving machine learning schemes over the last ten years, after discussing the importance of privacy-preserving techniques. In response to the diversity of Internet services, data services based on machine learning are now available for various applications, including risk assessment and image recognition. In light of open access to datasets and not fully trusted environments, machine learning-based applications face enormous security and privacy risks. In turn, it presents studies conducted to address privacy issues and a series of proposed solutions for ensuring privacy protection in machine learning tasks involving multiple parties. In closing, the book reviews state-of-the-art privacy-preserving techniques and examines the security threats they face.
The proliferation of data-driven services, particularly in risk assessment and image recognition, has amplified the critical need for robust privacy-preserving machine learning techniques. As machine learning applications increasingly operate in environments where data is openly accessible and trust is not guaranteed, they face significant security and privacy vulnerabilities. This book addresses these challenges by presenting a comprehensive review of the evolution of privacy-preserving machine learning schemes over the past decade, detailing studies conducted to tackle privacy issues and proposing solutions for multi-party machine learning tasks. It concludes by examining the current state of privacy-preserving technologies and the security threats they encounter.
This book offers a comprehensive examination of privacy-preserving machine learning, a critical field given the increasing reliance on data services and the inherent security risks. The authors meticulously trace the evolution of these techniques over the past decade, highlighting the challenges posed by open access to data and untrusted environments. By presenting a series of studies and proposed solutions for multi-party learning, the book aims to equip readers with an understanding of current advancements and the security threats that persist. The work is positioned as a thorough overview for those seeking to navigate the complex landscape of data privacy in machine learning.
Page Count:
88
Publication Date:
2022-03-15
Publisher:
Springer Nature Singapore
ISBN-10:
981169138X
ISBN-13:
9789811691386
No comments yet. Be the first to share your thoughts!