Aegis: A Correlation-Based Data Masking Advisor for Data Sharing Ecosystems

2025-10-12

AI Summary

In data sharing, anonymization incurs utility loss, and downstream machine learning performance is highly sensitive to masking configuration choices—necessitating efficient selection of optimal configurations. Method: We propose a privacy-utility-balancing middleware framework centered on a utility optimizer that tracks feature-label dependency changes. Leveraging lightweight data summaries (e.g., 1D histograms) and iterative proportional fitting (IPF), it estimates joint distributions without accessing raw data, supporting diverse correlation metrics—including g³, mutual information, and chi-square—while avoiding explicit data reconstruction. Contribution/Results: The framework enables automatic, privacy-preserving recommendation of optimal masking configurations. Experiments show an order-of-magnitude improvement in search efficiency over baselines, while masked data retain predictive performance comparable to unmasked baselines—significantly mitigating utility degradation induced by anonymization.

Technology Category

• Machine Learning: Privacy
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Data-sharing ecosystems enable entities -- such as providers, consumers, and intermediaries -- to access, exchange, and utilize data for various downstream tasks and applications. Due to privacy concerns, data providers typically anonymize datasets before sharing them; however, the existence of multiple masking configurations results in masked datasets with varying utility. Consequently, a key challenge lies in efficiently determining the optimal masking configuration that maximizes a dataset's utility. This paper presents AEGIS, a middleware framework for identifying the optimal masking configuration for machine learning datasets that consist of features and a class label. We introduce a utility optimizer that minimizes predictive utility deviation -- a metric based on the changes in feature-label correlations before and after masking. Our framework leverages limited data summaries (such as 1D histograms) or none to estimate the feature-label joint distribution, making it suitable for scenarios where raw data is inaccessible due to privacy restrictions. To achieve this, we propose a joint distribution estimator based on iterative proportional fitting, which allows supporting various feature-label correlation quantification methods such as g3, mutual information, or chi-square. Our experimental evaluation on real-world datasets shows that AEGIS identifies optimal masking configurations over an order of magnitude faster, while the resulting masked datasets achieve predictive performance on downstream ML tasks that is on par with baseline approaches.

Problem

• Optimizing data masking configurations to maximize dataset utility
• Minimizing predictive utility deviation through feature-label correlation analysis
• Estimating joint distributions without raw data access for privacy preservation

Innovation

• Correlation-based masking advisor for data sharing
• Utility optimizer minimizing predictive utility deviation
• Joint distribution estimator using iterative proportional fitting