When Machine Learning Meets Privacy: A Survey and Outlook
arXiv:2011.11819
Abstract
The newly emerged machine learning (e.g. deep learning) methods have become a strong driving force to revolutionize a wide range of industries, such as smart healthcare, financial technology, and surveillance systems. Meanwhile, privacy has emerged as a big concern in this machine learning-based artificial intelligence era. It is important to note that the problem of privacy preservation in the context of machine learning is quite different from that in traditional data privacy protection, as machine learning can act as both friend and foe. Currently, the work on the preservation of privacy and machine learning (ML) is still in an infancy stage, as most existing solutions only focus on privacy problems during the machine learning process. Therefore, a comprehensive study on the privacy preservation problems and machine learning is required. This paper surveys the state of the art in privacy issues and solutions for machine learning. The survey covers three categories of interactions between privacy and machine learning: (i) private machine learning, (ii) machine learning aided privacy protection, and (iii) machine learning-based privacy attack and corresponding protection schemes. The current research progress in each category is reviewed and the key challenges are identified. Finally, based on our in-depth analysis of the area of privacy and machine learning, we point out future research directions in this field.
This work is accepted by ACM Computing Surveys
References in corpus (27)
- Machine Learning in Automated Text Categorization
- Deep Learning with Differential Privacy
- Federated Learning: Strategies for Improving Communication Efficiency
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Renyi Differential Privacy
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Data Synthesis based on Generative Adversarial Networks
- Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
- Synthesizing Tabular Data using Generative Adversarial Networks
- Differential Privacy and Machine Learning: a Survey and Review
- Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
- Split learning for health: Distributed deep learning without sharing raw patient data
- Understanding Membership Inferences on Well-Generalized Learning Models
- Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
- Defeating Image Obfuscation with Deep Learning
- Privacy-preserving Machine Learning through Data Obfuscation
- Differentially Private Releasing via Deep Generative Model (Technical Report)
- On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches
- Distributed Differentially-Private Algorithms for Matrix and Tensor Factorization
- Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries
- Scalable Differential Privacy with Certified Robustness in Adversarial Learning
- Defense Against the Dark Arts: An overview of adversarial example security research and future research directions
- AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
- Privacy-preserving Prediction
- Generative Models for Simulating Mobility Trajectories