Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey

The rapid advancement of generative artificial intelligence (Gen-AI) has facilitated the effortless creation of high-quality images, while simultaneously raising critical concerns regarding intellectual property protection, authenticity, and accountability. Watermarking has emerged as a promising solution to these challenges by distinguishing AI-generated images from natural content, ensuring provenance, and fostering trustworthy digital ecosystems. This paper presents a comprehensive survey of the current state of AI-generated image watermarking, addressing five key dimensions: (1) formalization of image watermarking systems; (2) an overview and comparison of diverse watermarking techniques; (3) evaluation methodologies with respect to visual quality, capacity, and detectability; (4) vulnerabilities to malicious attacks; and (5) prevailing challenges and future directions. The survey aims to equip researchers with a holistic understanding of AI-generated image watermarking technologies, thereby promoting their continued development.

Key Contributions

Comprehensive taxonomy and comparison of AI-generated image watermarking techniques across diverse approaches
Structured evaluation methodology covering visual quality, capacity, and detectability dimensions
Analysis of vulnerabilities to malicious attacks on watermarks and identification of open challenges and future research directions

🛡️ Threat Analysis

Output Integrity Attack

The survey is entirely focused on watermarking AI-generated image outputs for provenance, authenticity, and distinguishing AI-generated content from natural images — plus vulnerabilities to malicious attacks on those watermarks (removal/forgery). This is squarely output integrity and content provenance, not model IP protection (ML05), as the watermarks reside in generated image content, not model weights.