Shapley-Value-Based Feature Attribution for Data Masking

2026-07-30

AI Summary

This work addresses the ongoing challenge of jointly optimizing disclosure risk and data utility at the feature level in privacy-preserving data processing. It introduces, for the first time, Shapley values into the domain of data anonymization, proposing a unified feature-attribution-based framework that guides the anonymization process by quantifying each feature’s marginal contribution to both risk and utility. The approach is agnostic to specific anonymization strategies, model architectures, and evaluation metrics, thereby offering strong generality. Experimental results demonstrate that the proposed framework significantly reduces disclosure risk while effectively preserving data utility, enabling fine-grained, feature-level trade-offs between privacy and utility.

Abstract

Despite its many benefits, widespread access to individuals' personal data also causes severe privacy concerns for consumers, companies, and policymakers. This study proposes a novel framework that adapts the Shapley-value-based feature attribution approach to the problem domain of data privacy by capturing the two crucial dimensions of data privacy---disclosure risk and data utility. Our proposed framework takes a holistic view of data masking through a fair feature attribution approach based on Shapley values. Different from the existing literature that mostly focuses on the risk-utility tradeoff at the dataset level, the proposed framework addresses the tradeoff at the feature level. Furthermore, the proposed framework is agnostic to data masking methods, statistical and machine learning methods, and data utility and disclosure risk evaluation metrics. Experimental results show that our proposed method can effectively reduce disclosure risk while preserving data utility.

Problem

• data privacy
• disclosure risk
• data utility
• feature attribution
• data masking

Innovation

• Shapley value
• feature attribution
• data masking
• privacy-utility tradeoff
• disclosure risk