Description
Book SynopsisThis book presents the data privacy protection which has been extensively applied in our current era of big data. However, research into big data privacy is still in its infancy. Given the fact that existing protection methods can result in low data utility and unbalanced trade-offs, personalized privacy protection has become a rapidly expanding research topic.In this book, the authors explore emerging threats and existing privacy protection methods, and discuss in detail both the advantages and disadvantages of personalized privacy protection. Traditional methods, such as differential privacy and cryptography, are discussed using a comparative and intersectional approach, and are contrasted with emerging methods like federated learning and generative adversarial nets.
The advances discussed cover various applications, e.g. cyber-physical systems, social networks, and location-based services. Given its scope, the book is of interest to scientists, policy-makers, researchers, and postgraduates alike.
Table of Contents· Chapter 1: Introduction
o Privacy research landscape
o Personalized privacy overview
o Contribution of this book
o Remainder of the book
· Chapter 2: Current Methods of Privacy Protection
o Cryptography based methods
o Differential privacy methods
o Anonymity-based methods
o Clustering-base methods
o Machine learning and AI methods
· Chapter 3: Privacy Attacks
o Attack classification
o Rationale of the attacks
o The comparison of attacks
· Chapter 4: Personalize Privacy Defense
o Personalized privacy in cyber-physical systems
o Personalized privacy in social networks
o Personalized privacy in smart city
o Personalized privacy in location-based services
o Personalized privacy on the rise
· Chapter 5: Future Directions
o Trade-off optimization
o Decentralized privacy protection
o Privacy-preserving federated learning
o Federated generative adversarial nets
· Chapter6: Summary and Outlook
