Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size
This addresses the need for traceability and integrity verification in AI-generated images, though it is incremental by building on traditional watermarking schemes.
The paper tackles the problem of embedding high-payload textual descriptions into AI-generated images for semantic watermarking, achieving robust retrieval even after image processing and AI inpainting.
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.