More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence

Abstract

Artificial Intelligence (AI) has attracted a great deal of attention in recent years. However, alongside all its advancements, problems have also emerged, such as privacy violations, security issues and model fairness. Differential privacy, as a promising mathematical model, has several attractive properties that can help solve these problems, making it quite a valuable tool. For this reason, differential privacy has been broadly applied in AI but to date, no study has documented which differential privacy mechanisms can or have been leveraged to overcome its issues or the properties that make this possible. In this paper, we show that differential privacy can do more than just privacy preservation. It can also be used to improve security, stabilize learning, build fair models, and impose composition in selected areas of AI. With a focus on regular machine learning, distributed machine learning, deep learning, and multi-agent systems, the purpose of this article is to deliver a new view on many possibilities for improving AI performance with differential privacy techniques.

References in corpus (11)

• Deep Learning with Differential Privacy
• Federated Learning: Strategies for Improving Communication Efficiency
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
• An Introduction to Deep Reinforcement Learning
• Improving fairness in machine learning systems: What do industry practitioners need?
• A Survey and Critique of Multiagent Deep Reinforcement Learning
• Technical Privacy Metrics: a Systematic Survey
• Advanced Probabilistic Couplings for Differential Privacy
• Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination
• Differential Privacy for the Analyst via Private Equilibrium Computation

Cited by in corpus (8)

• From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security
• Adversarial Attacks Against Deep Generative Models on Data: A Survey
• Privacy Intelligence: A Survey on Image Privacy in Online Social Networks
• Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
• Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
• GeoLocator: a location-integrated large multimodal model for inferring geo-privacy
• Differentially Private GANs for Generating Synthetic Indoor Location Data
• Memorization of Named Entities in Fine-tuned BERT Models