Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques

2021/09/06 by Ashly Lau, Lau, Ashly, Jonathan Passerat‐Palmbach +1 · 1 citation
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2109.02496

openalex publication_date 2021/09/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning pipeline, in particular during the preprocessing phase. Our contributions are twofold: we adapt a privacy violation detection framework based on statistical methods to empirically measure privacy levels of machine learning pipelines, and apply the newly created framework to show that resampling techniques used when dealing with imbalanced datasets cause the resultant model to leak more privacy. These results highlight the need for developing private preprocessing techniques.

Cited by

• SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling

Related

• A General Framework for Auditing Differentially Private Machine Learning
• Three Tools for Practical Differential Privacy
• Differential Privacy and Machine Learning: a Survey and Review
• Tight Auditing of Differentially Private Machine Learning
• Evaluating Differentially Private Machine Learning in Practice