Differential Privacy and Machine Learning: a Survey and Review
arXiv:1412.7584
Abstract
The objective of machine learning is to extract useful information from data, while privacy is preserved by concealing information. Thus it seems hard to reconcile these competing interests. However, they frequently must be balanced when mining sensitive data. For example, medical research represents an important application where it is necessary both to extract useful information and protect patient privacy. One way to resolve the conflict is to extract general characteristics of whole populations without disclosing the private information of individuals. In this paper, we consider differential privacy, one of the most popular and powerful definitions of privacy. We explore the interplay between machine learning and differential privacy, namely privacy-preserving machine learning algorithms and learning-based data release mechanisms. We also describe some theoretical results that address what can be learned differentially privately and upper bounds of loss functions for differentially private algorithms. Finally, we present some open questions, including how to incorporate public data, how to deal with missing data in private datasets, and whether, as the number of observed samples grows arbitrarily large, differentially private machine learning algorithms can be achieved at no cost to utility as compared to corresponding non-differentially private algorithms.
References in corpus (2)
Cited by in corpus (42)
- Algorithms that Remember: Model Inversion Attacks and Data Protection Law
- Differential Privacy-enabled Federated Learning for Sensitive Health Data
- When Machine Learning Meets Privacy: A Survey and Outlook
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
- Differentially Private Random Decision Forests using Smooth Sensitivity
- Differential Privacy for Eye-Tracking Data
- Artificial Intelligence for Social Good: A Survey
- Differentially Private Synthetic Data: Applied Evaluations and Enhancements
- Differential Privacy in Natural Language Processing: The Story So Far
- Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification
- Decision Tree Classification with Differential Privacy: A Survey
- Differential Privacy Techniques for Cyber Physical Systems: A Survey
- DP-LSTM: Differential Privacy-inspired LSTM for Stock Prediction Using Financial News
- SPEED: Secure, PrivatE, and Efficient Deep learning
- COVID-19 Imaging Data Privacy by Federated Learning Design: A Theoretical Framework
- Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspective
- Privacy for All: Demystify Vulnerability Disparity of Differential Privacy against Membership Inference Attack
- Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics
- Privacy-Preserving Blockchain Based Federated Learning with Differential Data Sharing
- Automated Anonymisation of Visual and Audio Data in Classroom Studies
- AI and Ethics -- Operationalising Responsible AI
- Distributed Differentially Private Computation of Functions with Correlated Noise
- Privacy-preserving Active Learning on Sensitive Data for User Intent Classification
- Improved Differentially Private Decentralized Source Separation for fMRI Data
- Proof of Swarm Based Ensemble Learning for Federated Learning Applications
- Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks
- Efficient hyperparameter optimization by way of PAC-Bayes bound minimization
- Data collaboration analysis for distributed datasets
- Have you forgotten? A method to assess if machine learning models have forgotten data
- Modeling Disclosive Transparency in NLP Application Descriptions
- Know Your Model (KYM): Increasing Trust in AI and Machine Learning
- Differential Privacy for Credit Risk Model
- Artificial Intelligence Narratives: An Objective Perspective on Current Developments
- Interpretable collaborative data analysis on distributed data
- Theoretical Model and Practical Considerations for Data Lineage Reconstruction
- Differentially Private M-band Wavelet-Based Mechanisms in Machine Learning Environments
- Improving Utility of Differentially Private Mechanisms through Cryptography-based Technologies: a Survey
- Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent
- A Framework for Behavior Privacy Preserving in Radio Frequency Signal
- Confidential Machine Learning on Untrusted Platforms: A Survey
- Secure Metric Learning via Differential Pairwise Privacy
- Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques