Metraipolis › archive › dc_10e7ac0cc649
Protective Perturbations Must Survive the Resize: Scale-Robust Image Immunization against Malicious Editing — arXiv:2610.07464
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07464
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:07:09.016Z
- SHA-256 of the archived text
020164e96b3de44bb59dc5dff3a9d42c96b13a07fcacfd01c6182da77de2ac94- Stable URL of this page
https://metraipolis.com/documento/dc_10e7ac0cc649
How to cite
Protective Perturbations Must Survive the Resize: Scale-Robust Image Immunization against Malicious Editing — arXiv:2610.07464 — arXiv (en), https://arxiv.org/abs/2610.07464 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10e7ac0cc649 (Metraipolis archive dc_10e7ac0cc649, sha256 020164e96b3de44bb59dc5dff3a9d42c96b13a07fcacfd01c6182da77de2ac94)
BibTeX
@misc{dc10e7ac0cc649,
title = {Protective Perturbations Must Survive the Resize: Scale-Robust Image Immunization against Malicious Editing — arXiv:2610.07464},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07464},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10e7ac0cc649; sha256 020164e96b3de44bb59dc5dff3a9d42c96b13a07fcacfd01c6182da77de2ac94},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07464. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Protective perturbations aim to stop malicious instruction-guided editing of personal photos, but they are optimized and evaluated at the editor's working resolution, whereas shared photos have 10 megapixels or more and editors first downscale them by an unknown factor. We model this resize as a frequency-selective channel. In this model, a perturbation computed at the native resolution decays with the downscaling factor and is weak even without a resize, and a perturbation computed at a fixed working resolution protects only a window of scales. The best worst-case protection over an unknown range of scales degrades only logarithmically with the width of the range, and averaging over scales does not reach it. Guided by this analysis, we propose SRIM, which samples a grid of anchor scales covering the whole range, with weights that favor the currently weakest scale, at the cost of standard expectation over transformation. On full-resolution photos of 9 to 30 megapixels and downscaling factors from 2 to 8, SRIM raises the worst-case disruption of FLUX.2-klein edits from 0.192 LPIPS, attained by the strongest published protection, to 0.463. At equal visibility, it roughly doubles the protection. The same protected photos also protect against the 9B model and against FLUX.2-dev, with worst cases of 0.450 and 0.386 against at most 0.184 for published protections, and SRIM leads on InstructPix2Pix as well. 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/2610.07464 — 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 2026-10-07T12:37:32.886Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).