Metraipolis › archive › dc_fffcb8cf2a4c
Gaussian Image Steganography via Parameter-Domain Keyed Embeddings — arXiv:2609.32131
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32131
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:50:43.807Z
- SHA-256 of the archived text
bc9c2aa75f7302f100fd0cc524ec2a7701a09d837e795fabbc1df41644a2fbec- Stable URL of this page
https://metraipolis.com/documento/dc_fffcb8cf2a4c
How to cite
Gaussian Image Steganography via Parameter-Domain Keyed Embeddings — arXiv:2609.32131 — arXiv (en), https://arxiv.org/abs/2609.32131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fffcb8cf2a4c (Metraipolis archive dc_fffcb8cf2a4c, sha256 bc9c2aa75f7302f100fd0cc524ec2a7701a09d837e795fabbc1df41644a2fbec)
BibTeX
@misc{dcfffcb8cf2a4c,
title = {Gaussian Image Steganography via Parameter-Domain Keyed Embeddings — arXiv:2609.32131},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32131},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fffcb8cf2a4c; sha256 bc9c2aa75f7302f100fd0cc524ec2a7701a09d837e795fabbc1df41644a2fbec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
2D Gaussian-based image representation is becoming increasingly popular, and our work proposes a new approach to steganography by embedding information within Gaussian parameters rather than image pixels. We first fit the parameters of this representation to the target image and employ a secret key to select a subset of these parameters for fine-tuning, allowing us to embed an 8-bit message while maintaining high visual fidelity in the reconstructed image. Thirty fitting experiments on three synthetic images show that the correct key can recover the message without error, while decoding with incorrect keys yields a Bit Error Rate (BER) of $0.543$, close to random guessing. Compared with random selection using the key, selecting the least-disturbing edits recovers the message more reliably (one-sided $p=0.031$), and the average PSNR cost is only $0.091$ dB in visual quality. The embedding method transfers to 112 natural images at $256\times256$ using 4,096 Gaussians. The correct-key BER is $0.000$, and decoding under a wrong key stays close to random guessing at $0.520$. Our method embeds the payload through three Gaussian parameter types: log-anisotropy, opacity, and color luminance. In a separate nine-fit reduced setting, color luminance is removed, so the payload uses two instead of three parameter types, a $33.3\%$ reduction; all 256 Gaussians remain in the fitted representation. The correct key still recovers the message without error. However, wrong-key BER rises from $0.514$ to $0.571$, moving farther from random guessing ($0.5$). Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR). Pagina del lavoro: https://arxiv.org/abs/2609.32131 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T23:29:26.965Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).