Automatic Discovery of Privacy–Utility Pareto Fronts
By Brendan Avent, Javier I. González, Tom Diethe, Andrei Paleyes, Borja Balle. 2019
32 citations recorded by the source corpus.
Abstract Differential privacy is a mathematical framework for privacy-preserving data analysis. Changing the hyperparameters of a differentially private algorithm allows one to trade off privacy and utility in a principled way. Quantifying this trade-off in advance is essential to decision-makers tasked with deciding how much privacy can be provided in a particular application while maintaining acceptable utility. Analytical utility guarantees offer a rigorous tool to reason about this tradeoff, but are generally only available for relatively simple problems. For more complex tasks, such as training neural networks under differential privacy, the utility achieved by a given algorithm can only be measured empirically. This paper presents a Bayesian optimization methodology for efficiently characterizing the privacy– utility trade-off of any differentially private algorithm using only empirical measurements of its utility. The versatility of our method is illustrated on a number of machine learning tasks involving multiple models, optimizers, and datasets.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Abhradeep Thakurta
- Shuang Song
- Nicolas Papernot
- Steve Chien
- Ú. Erlingsson
- Florian Tramèr
- Nicholas Carlini
- Andrei Paleyes
Citations in the corpus
- Tempered Sigmoid Activations for Deep Learning with Differential Privacy (2020, methodology): “Figure 3 visualizes the privacy-utility Pareto curve (Avent et al. 2019) of the ReLU and tanh models trained with DP-SGD for all three datasets.”
- Challenges in Deploying Machine Learning: A Survey of Case Studies (2020, background): “Navigating the trade-off between privacy and utility is considered an open challenge for practitioners dealing with sensitive data [53].”