English

SWIFT: Semantic Watermarking for Image Forgery Thwarting

Cryptography and Security 2025-10-14 v2 Artificial Intelligence Computer Vision and Pattern Recognition Multimedia

Abstract

This paper proposes a novel approach towards image authentication and tampering detection by using watermarking as a communication channel for semantic information. We modify the HiDDeN deep-learning watermarking architecture to embed and extract high-dimensional real vectors representing image captions. Our method improves significantly robustness on both malign and benign edits. We also introduce a local confidence metric correlated with Message Recovery Rate, enhancing the method's practical applicability. This approach bridges the gap between traditional watermarking and passive forensic methods, offering a robust solution for image integrity verification.

Keywords

Cite

@article{arxiv.2407.18995,
  title  = {SWIFT: Semantic Watermarking for Image Forgery Thwarting},
  author = {Gautier Evennou and Vivien Chappelier and Ewa Kijak and Teddy Furon},
  journal= {arXiv preprint arXiv:2407.18995},
  year   = {2025}
}

Comments

Accepted at IEEE WIFS 2024; Code released at : https://github.com/gautierevn/swift_watermarking

R2 v1 2026-06-28T17:55:03.618Z