| Description |
1 online resource |
| Series |
SpringerBriefs on cyber security systems and networks |
|
SpringerBriefs on cyber security systems and networks.
|
| Contents |
Intro -- Preface -- Acknowledgements -- Contents -- Acronyms -- 1 Introduction -- 1.1 Background -- 1.2 Motivation -- 1.3 Outline -- References -- 2 Preliminaries -- 2.1 Classical Privacy-Preserving Technologies -- 2.1.1 Group-Based Anonymity -- 2.1.2 Cryptographic Method -- 2.1.3 Differential Privacy -- 2.1.4 Secure Enclaves -- 2.2 Deep Learning -- 2.2.1 Outline of Deep Learning -- 2.2.2 Deep Learning Layers -- 2.2.3 Convolutional Neural Network (CNN) -- 2.2.4 Generative Adversarial Network (GAN) -- 2.2.5 Support Vector Machine -- 2.2.6 Recurrent Neural Network -- 2.2.7 K-Means Clustering |
|
2.2.8 Reinforcement Learning -- References -- 3 X-Based PPDL -- 3.1 HE-Based PPDL -- 3.2 Secure MPC-Based PPDL -- 3.3 Differential Privacy-Based PPDL -- 3.4 Secure Enclaves-Based PPDL -- 3.5 Hybrid-Based PPDL -- References -- 4 Pros and Cons of X-Based PPDL -- 4.1 Metrics for Comparison -- 4.2 Comparison of X-Based PPDL -- 4.3 Weaknesses and Possible Solutions of X-Based PPDL -- 4.3.1 Model Parameter Transmission Approach -- 4.3.2 Data Transmission Approach -- 4.3.3 Analysis and Summary -- References -- 5 Privacy-Preserving Federated Learning -- 5.1 Overview -- 5.2 Function Specific PPFL |
|
5.2.1 Fairness -- 5.2.2 Integrity -- 5.2.3 Correctness -- 5.2.4 Adaptive -- 5.2.5 Flexibility -- 5.3 Application Specific PPFL -- 5.3.1 Mobile Devices -- 5.3.2 Medical Imaging -- 5.3.3 Traffic Flow Prediction -- 5.3.4 Healthcare -- 5.3.5 Android Malware Detection -- 5.3.6 Edge Computing -- 5.4 Summary -- References -- 6 Attacks on Deep Learning and Their Countermeasures -- 6.1 Adversarial Model on PPDL -- 6.1.1 Adversarial Model Based on the Behavior -- 6.1.2 Adversarial Model Based on the Power -- 6.1.3 Adversarial Model Based on Corruption Type -- 6.2 Security Goals of PPDL |
|
6.3 Attacks on PPDL -- 6.3.1 Membership Inference Attack -- 6.3.2 Model Inversion Attack -- 6.3.3 Model Extraction Attack -- 6.4 Countermeasure and Defense Mechanism -- References -- Appendix Concluding Remarks and Further Work |
| Summary |
This book discusses the state-of-the-art in privacy-preserving deep learning (PPDL), especially as a tool for machine learning as a service (MLaaS), which serves as an enabling technology by combining classical privacy-preserving and cryptographic protocols with deep learning. Google and Microsoft announced a major investment in PPDL in early 2019. This was followed by Google's infamous announcement of private Join and Compute, an open source PPDL tools based on secure multi-party computation (secure MPC) and homomorphic encryption (HE) in June of that year. One of the challenging issues concerning PPDL is selecting its practical applicability despite the gap between the theory and practice. In order to solve this problem, it has recently been proposed that in addition to classical privacy-preserving methods (HE, secure MPC, differential privacy, secure enclaves), new federated or split learning for PPDL should also be applied. This concept involves building a cloud framework that enables collaborative learning while keeping training data on client devices. This successfully preserves privacy and while allowing the framework to be implemented in the real world. This book provides fundamental insights into privacy-preserving and deep learning, offering a comprehensive overview of the state-of-the-art in PPDL methods. It discusses practical issues, and leveraging federated or split-learning-based PPDL. Covering the fundamental theory of PPDL, the pros and cons of current PPDL methods, and addressing the gap between theory and practice in the most recent approaches, it is a valuable reference resource for a general audience, undergraduate and graduate students, as well as practitioners interested learning about PPDL from the scratch, and researchers wanting to explore PPDL for their applications |
| Bibliography |
Includes bibliographical references |
| Notes |
Online resource; title from PDF title page (SpringerLink, viewed August 3, 2021) |
| Subject |
Machine learning -- Security measures
|
| Form |
Electronic book
|
| Author |
Tanuwidjaja, Harry Chandra, author
|
| ISBN |
9789811637643 |
|
9811637644 |
|
