Description
Book SynopsisPrivacy-preserving computing aims to protect the personal information of users while capitalizing on the possibilities offered by big data. This practical introduction for students, researchers, and industry practitioners presents a systematic tour of recent advances in privacy-preserving methods for real-world problems in analytics and AI.
Trade Review'While we are witnessing revolutionary changes in AI technology empowered by deep learning and large-scale computing, data privacy for trusted machine learning plays an essential role in safe and reliable AI deployment. This book introduces fundamental concepts and advanced techniques for privacy-preserving computation for data mining and machine learning, which serve as a foundation for safe and secure AI development and deployment.' Pin-Yu Chen, IBM Research
Table of Contents1. Introduction to privacy-preserving computing; 2. Secret sharing; 3. Homomorphic encryption; 4. Oblivious transfer; 5. Garbled circuit; 6. Differential privacy; 7. Trusted execution environment; 8. Federated learning; 9. Privacy-preserving computing platforms; 10. Case studies of privacy-preserving computing; 11. Future of privacy-preserving computing; References; Index.
