Metraipolis › archive › dc_248b64491cbb
A Valid Watermark Is Not a Valid Identity: Spatial-Spectral Adversarial Face Evasion with Watermark Preservation — arXiv:2610.20278
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20278
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:57:07.550Z
- SHA-256 of the archived text
84e585c78fb5e9179eb0b821daa00a429fb067f15dbf10b47165177d99782924- Stable URL of this page
https://metraipolis.com/documento/dc_248b64491cbb
How to cite
A Valid Watermark Is Not a Valid Identity: Spatial-Spectral Adversarial Face Evasion with Watermark Preservation — arXiv:2610.20278 — arXiv (en), https://arxiv.org/abs/2610.20278 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_248b64491cbb (Metraipolis archive dc_248b64491cbb, sha256 84e585c78fb5e9179eb0b821daa00a429fb067f15dbf10b47165177d99782924)
BibTeX
@misc{dc248b64491cbb,
title = {A Valid Watermark Is Not a Valid Identity: Spatial-Spectral Adversarial Face Evasion with Watermark Preservation — arXiv:2610.20278},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20278},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_248b64491cbb; sha256 84e585c78fb5e9179eb0b821daa00a429fb067f15dbf10b47165177d99782924},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20278. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Facial image watermarking can support traceability and certification in biometric pipelines, but provenance or manipulation detection alone does not guarantee reliable biometric identity. We introduce a watermark-preserving face evasion attack that targets this gap under a black-box watermarking setting, without access to the watermarking components. The proposed PGD-L_2 attack guides adversarial perturbations with spatial and spectral preservation terms to reduce face-recognition similarity while limiting pixel-level distortion and high-frequency changes that may interfere with hidden watermark cues. Evaluated on controlled facial images with two watermarking schemes, two face-recognition models, and two datasets, the attack achieves evasion rates above 92% at operational thresholds while preserving watermark recovery above 93% for StegaFormer and above 99.7% for FaceSigns, with visual quality above 47dB PSNR at epsilon_2=2.0. These results expose a structural gap in watermark-based facial certification: a face image can remain watermark-valid and visually faithful while becoming biometrically unreliable. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.20278 — 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 2026-10-15T21:38:29.529Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).