Название: Sustainable Development Using Private AI: Security Models and Applications
Автор: Uma Maheswari V, Rajanikanth Aluvalu
Издательство: CRC Press
Год: 2025
Страниц: 319
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB

This book covers the fundamental concepts of Private AI and its applications. It also covers fusion of Private AI with cutting-edge technologies like cloud computing, Federated Learning and computer vision.

Security Models and Applications for Sustainable Development Using Private AI reviews various encryption algorithms used for providing security in Private AI. It discusses the role of training Machine Learning and Deep learning technologies in Private AI. The book provides case studies of using Private AI in various application areas such as purchasing, education, entertainment, medical diagnosis, predictive care, conversational personal assistants, wellness apps, early disease detection, and recommendation systems. The authors provide additional knowledge to handling the customer’s data securely and efficiently. It also provides multi-model dataset storage approaches along with the traditional approaches like anonymization of data and differential privacy mechanisms.

Private AI, also known as privacy-preserving AI or confdential AI, is a subset of Artifcial Intelligence that focuses on developing techniques and technologies to protect the privacy and confdentiality of data and models used in AI applications. Privacy is a critical concern in the feld of AI because many AI systems require access to sensitive and personal data, which, if mishandled, can lead to privacy breaches and other adverse consequences.

Public AI trains its models on publicly available data on the internet. It uses information that is not private to a user or an organization. It is an algorithm that uses public datasets, often to improve customer service. The organizations can misuse these datasets and exploit the customer’s rights. To ensure a safe and secure AI experience, Private AI has come into the picture. Unlike public AI, private AI uses datasets that are private to a particular individual or organization. This avoids creating a collective intelligence that could help other competitors.

The target audience includes undergraduate and postgraduate students in Computer Science, Information technology, Electronics and Communication Engineering and related disciplines. This book is also a one stop reference point for professionals, security researchers, scholars, various government agencies and security practitioners, and experts working in the cybersecurity Industry specifically in the R & D division.