DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learning

12/24/2021
by   Ismat Jarin, et al.
0

Differential Privacy (DP) has emerged as a rigorous formalism to reason about quantifiable privacy leakage. In machine learning (ML), DP has been employed to limit inference/disclosure of training examples. Prior work leveraged DP across the ML pipeline, albeit in isolation, often focusing on mechanisms such as gradient perturbation. In this paper, we present, DP-UTIL, a holistic utility analysis framework of DP across the ML pipeline with focus on input perturbation, objective perturbation, gradient perturbation, output perturbation, and prediction perturbation. Given an ML task on privacy-sensitive data, DP-UTIL enables a ML privacy practitioner perform holistic comparative analysis on the impact of DP in these five perturbation spots, measured in terms of model utility loss, privacy leakage, and the number of truly revealed training samples. We evaluate DP-UTIL over classification tasks on vision, medical, and financial datasets, using two representative learning algorithms (logistic regression and deep neural network) against membership inference attack as a case study attack. One of the highlights of our results is that prediction perturbation consistently achieves the lowest utility loss on all models across all datasets. In logistic regression models, objective perturbation results in lowest privacy leakage compared to other perturbation techniques. For deep neural networks, gradient perturbation results in lowest privacy leakage. Moreover, our results on true revealed records suggest that as privacy leakage increases a differentially private model reveals more number of member samples. Overall, our findings suggest that to make informed decisions as to which perturbation mechanism to use, a ML privacy practitioner needs to examine the dynamics between optimization techniques (convex vs. non-convex), perturbation mechanisms, number of classes, and privacy budget.

READ FULL TEXT
research
04/03/2022

A Differentially Private Framework for Deep Learning with Convexified Loss Functions

Differential privacy (DP) has been applied in deep learning for preservi...
research
07/25/2023

Accuracy Amplification in Differentially Private Logistic Regression: A Pre-Training Approach

Machine learning (ML) models can memorize training datasets. As a result...
research
11/21/2022

Privacy in Practice: Private COVID-19 Detection in X-Ray Images

Machine learning (ML) can help fight the COVID-19 pandemic by enabling r...
research
05/10/2023

DPMLBench: Holistic Evaluation of Differentially Private Machine Learning

Differential privacy (DP), as a rigorous mathematical definition quantif...
research
06/27/2023

Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile

Differential privacy (DP) is the prevailing technique for protecting use...
research
06/29/2021

Privacy Budget Scheduling

Machine learning (ML) models trained on personal data have been shown to...
research
03/24/2023

On the connection between the ABS perturbation methodology and differential privacy

This paper explores analytical connections between the perturbation meth...

Please sign up or login with your details

Forgot password? Click here to reset