Privacy-preserving deep learning [electronic resource] : a comprehensive survey / Kwangjo Kim, Harry Chandra Tanuwidjaja.

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