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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tondi, Benedetta, Costanzo, Andrea, Barni, Mauro
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916976919576576
author Tondi, Benedetta
Costanzo, Andrea
Barni, Mauro
author_facet Tondi, Benedetta
Costanzo, Andrea
Barni, Mauro
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24823
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size
Tondi, Benedetta
Costanzo, Andrea
Barni, Mauro
Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
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.
title Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size
topic Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2509.24823