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

2025-08-12

AI Summary

To address the lack of a unified quantitative standard for information leakage in selectively encrypted images, this paper proposes a privacy risk assessment method integrating information theory and deep learning. The core innovation is a mutual information estimation framework constructed within a CNN embedding space, combining empirical estimators with the Mutual Information Neural Estimation (MINE) optimization strategy to accurately characterize residual spatial dependencies and structural artifacts in encrypted images. Crucially, the method enables end-to-end leakage quantification without requiring access to original plaintext images. Extensive experiments across diverse selective encryption schemes demonstrate its effectiveness and robustness. Results show that the proposed model significantly improves detection sensitivity to information leakage, providing an interpretable, reproducible theoretical tool and practical methodology for evaluating image privacy protection.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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.

Problem

• Measure privacy leakage in selectively encrypted images
• Use mutual information estimators for leakage detection
• Develop probabilistic frameworks for spatial dependencies analysis

Innovation

• Uses mutual information estimators for leakage detection
• Combines deep learning with information theory
• Analyzes encrypted image spatial dependencies