# Researchers Propose Turning Editing Models' Own Moderation Filters Into a Defense

MIRAGE adds perturbations to images so that AI editing systems refuse to alter them, an inversion of standard image-immunization approaches.

- Published: 2026-06-26T10:45:35.415Z
- Canonical: https://polylog.news/ai/2026-06-26/researchers-propose-turning-editing-models-own-moderation-fi
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CR (MIRAGE)](https://arxiv.org/abs/2606.26199)

A new paper, MIRAGE: Protecting against Malicious Image Editing via False Moderation, proposes a defense against the unauthorized manipulation of personal photographs by AI editing systems. The authors note that such systems let images be a…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-06-26/researchers-propose-turning-editing-models-own-moderation-fi (subscription information: https://polylog.news/pricing).