Image selective encryption analysis using mutual information in CNN based embedding space

TL;DR

This paper explores the use of mutual information estimators to detect information leakage in selectively encrypted images within CNN embedding spaces, addressing a gap in quantitative privacy measures for image data.

Contribution

It introduces the application of MI estimators, including MINE, to analyze privacy leakage in encrypted images, bridging deep learning, information theory, and cryptography.

Findings

Mutual information estimators can detect leakage in encrypted images.

Empirical and MINE estimators capture spatial dependencies in encrypted representations.

The approach offers a promising direction for quantifying image privacy risks.

Abstract

As digital data transmission continues to scale, concerns about privacy grow increasingly urgent - yet privacy remains a socially constructed and ambiguously defined concept, lacking a universally accepted quantitative measure. This work examines information leakage in image data, a domain where information-theoretic guarantees are still underexplored. At the intersection of deep learning, information theory, and cryptography, we investigate the use of mutual information (MI) estimators - in particular, the empirical estimator and the MINE framework - to detect leakage from selectively encrypted images. Motivated by the intuition that a robust estimator would require a probabilistic frameworks that can capture spatial dependencies and residual structures, even within encrypted representations - our work represent a promising direction for image information leakage estimation.