Metraipolis › archive › dc_2918eb101211

NullEdit: Stealthy Image Protection via VLM Condition Redirection — arXiv:2608.10870

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10870
License (as archived)
CC0-1.0
Archived
2026-10-19T06:30:30.600Z
SHA-256 of the archived text
0cafbe08d6e46b739116d7d5eef0583485d437ccb088063ec144cb08fbfddbfd
Stable URL of this page
https://metraipolis.com/documento/dc_2918eb101211

How to cite

NullEdit: Stealthy Image Protection via VLM Condition Redirection — arXiv:2608.10870 — arXiv (en), https://arxiv.org/abs/2608.10870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2918eb101211 (Metraipolis archive dc_2918eb101211, sha256 0cafbe08d6e46b739116d7d5eef0583485d437ccb088063ec144cb08fbfddbfd)
BibTeX
@misc{dc2918eb101211,
  title = {NullEdit: Stealthy Image Protection via VLM Condition Redirection — arXiv:2608.10870},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10870},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2918eb101211; sha256 0cafbe08d6e46b739116d7d5eef0583485d437ccb088063ec144cb08fbfddbfd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern image editors combine vision-language models (VLMs) with diffusion transformer backbones to modify a single reference image according to instructions without fine-tuning. This capability also enables unauthorized manipulation of publicly released images. Existing inference-time defenses either invalidate edits through conspicuous corruption, thereby exposing the protection, or allow them to proceed with identity or reference content drift, thereby failing to prevent the editing behavior itself. We instead target a stealthy and harmless no-op in which the requested edit is suppressed, the output remains natural and source-preserving without conspicuous artifacts or identity replacement, and harmful semantics requested by malicious instructions are absent. We propose NullEdit, which targets the VLM representation jointly formed from the reference image and instruction before it conditions the downstream DiT backbone. Using normal-edit and no-edit anchors, NullEdit redirects this representation, while cross-prompt gradient averaging transfers protection to held out instructions. Across Step1X-Edit and Qwen-Image-Edit on CelebA-HQ and VGGFace2, NullEdit reduces the EditReward IF score by 0.813 on average relative to the SOTA baseline while preserving subject identity and source content.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.10870 — 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 2026-10-19T06:25:27.292Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).