Image Privacy Protection: A Survey

TL;DR

This survey addresses the broad challenge of protecting image privacy across diverse scenarios and privacy goals. It introduces privacy-sensitive domains as a core classification axis and presents a three-layer framework—data-level, content-level, and feature-level—to unify protection strategies. The paper systematically reviews representative solutions in each layer: data-level methods (cryptography, compressed sensing, and neural networks), content-level approaches (filtering, synthesis, transformation, and encryption) with local/global objectives, and feature-level techniques (adversarial perturbations and synthetic methods) with reversible and irreversible variants. It also discusses design principles, robustness considerations, and non-robustness tradeoffs, and outlines challenges and directions such as dynamic revocability, user-centric control, and privacy in multimodal learning, highlighting the practical impact of a holistic framework for image privacy protection.

Abstract

Images serve as a crucial medium for communication, presenting information in a visually engaging format that facilitates rapid comprehension of key points. Meanwhile, during transmission and storage, they contain significant sensitive information. If not managed properly, this information may be vulnerable to exploitation for personal gain, potentially infringing on privacy rights and other legal entitlements. Consequently, researchers continue to propose some approaches for preserving image privacy and publish reviews that provide comprehensive and methodical summaries of these approaches. However, existing reviews tend to categorize either by specific scenarios, or by specific privacy objectives. This classification somewhat restricts the reader's ability to grasp a holistic view of image privacy protection and poses challenges in developing a total understanding of the subject that transcends different scenarios and privacy objectives. Instead of examining image privacy protection from a single aspect, it is more desirable to consider user needs for a comprehensive understanding. To fill this gap, we conduct a systematic review of image privacy protection approaches based on privacy protection goals. Specifically, we define the attribute known as privacy sensitive domains and use it as the core classification dimension to construct a comprehensive framework for image privacy protection that encompasses various scenarios and privacy objectives. This framework offers a deep understanding of the multi-layered aspects of image privacy, categorizing its protection into three primary levels: data-level, content-level, and feature-level. For each category, we analyze the main approaches and features of image privacy protection and systematically review representative solutions. Finally, we discuss the challenges and future directions of image privacy protection.

Figures (6)

• Figure 1: Differences in privacy requirements among different individuals.
• Figure 2: Different categories of image privacy protection.
• Figure 3: A framework of image privacy protection.
• Figure 4: Overview of the data-level image privacy protection.
• Figure 5: Overview of the content-level image privacy protection.