The Trade-Offs of Private Prediction
Machine learning models leak information about their training data every time they reveal a prediction. This is problematic when the training data needs to remain private. Private prediction methods limit how much information about the training data is leaked by each prediction. Private prediction can also be achieved using models that are trained by private training methods. In private prediction, both private training and private prediction methods exhibit trade-offs between privacy, privacy failure probability, amount of training data, and inference budget. Although these trade-offs are theoretically well-understood, they have hardly been studied empirically. This paper presents the first empirical study into the trade-offs of private prediction. Our study sheds light on which methods are best suited for which learning setting. Perhaps surprisingly, we find private training methods outperform private prediction methods in a wide range of private prediction settings.
Code (1)
Tasks
PredictionSimilar Papers 제목 키워드 기반
Optimized Tradeoffs for Private Prediction with Majority Ensembling
We study a classical problem in private prediction, the problem of computing an $(m\epsilon, \delta)$-differentially private majority of $K$ $(\epsilon, \Delta)$-differentially private algorithms for $1 \leq m \leq K$ an…
image-classificationImage ClassificationPredictionChasing Your Long Tails: Differentially Private Prediction in Health Care Settings
Machine learning models in health care are often deployed in settings where it is important to protect patient privacy. In such settings, methods for differentially private (DP) learning provide a general-purpose approac…
FairnessMortality PredictionPrivacy PreservingTime Series+2Privacy-Computation trade-offs in Private Repetition and Metaselection
A Private Repetition algorithm takes as input a differentially private algorithm with constant success probability and boosts it to one that succeeds with high probability. These algorithms are closely related to private…
Differentially private training of residual networks with scale normalisation
The training of neural networks with Differentially Private Stochastic Gradient Descent offers formal Differential Privacy guarantees but introduces accuracy trade-offs. In this work, we propose to alleviate these trade-…
Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection
Graph Neural Networks (GNNs) have proven to be highly effective in solving real-world learning problems that involve graph-structured data. However, GNNs can also inadvertently expose sensitive user information and inter…