Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size

ABSTRACT We propose a high-payload image watermarking method for textual embedding, where a semantic description of the image - which may also correspond to the input text prompt-, is embedded inside the image. In order to be able to robustly embed high payloads in large-scale images - such as those produced by modern AI generators - the proposed approach builds upon a traditional watermarking scheme that exploits orthogonal and turbo codes for improved robustness, and integrates frequency-domain embedding and perceptual masking techniques to enhance watermark imperceptibility. Experiments show that the proposed method is extremely robust against a wide variety of image processing, and the embedded text can be retrieved also after traditional and AI inpainting, permitting to unveil the semantic modification the image has undergone via image-text mismatch analysis. Index T erms-- watermarking of AI-generated content, post-generation watermarking, proactive deepfake detection, semantic manipulation detection 1. INTRODUCTION Modern AI models offer incredible benefits by enabling anyone to easily create extremely realistic images. Nonetheless, they also pose significant risks related to image misuse, including the spread of misinformation and potential public harm.