MIRAGE: Protecting against Malicious Image Editing via False Moderation

Computer Science > Cryptography and Security [Submitted on 24 Jun 2026] MIRAGE: Protecting against Malicious Image Editing via False Moderation Anshul Nasery, Ramnath Kumar, Cho-Jui Hsieh, Sewoong Oh The proliferation of AI-powered image editing systems raises serious concerns because it allows personal images to be arbitrarily manipulated at scale, with minimal effort, and a lower barrier to entry. Prior work on image immunization adds imperceptible perturbations to an image to protect against unauthorized manipulations. However, these methods usually require access to the model weights and the image manipulating prompt. This significantly limits their use, especially against powerful commercial image-editors such as GPT-Image, Gemini Flash Image (Nano Banana), and Grok Imagine. To address this, we take a system-level view of the problem and identify a previously unexplored attack surface common to all major commercial image editing systems: pre-generation safety this http URL than disrupting the generative model itself, we propose to immunize images by causing these moderation classifiers to flag images as policy-violating, triggering an automatic refusal regardless of the editing prompt. We operationalize this by adding adversarial perturbations to align our image to policy-violating concepts in the representation space of an ensemble of open-source embedding and moderation models. We call our method MIRAGE, which stands for Moderation Induced Resistance Against Generative Editing. We evaluate MIRAGE against multiple closed-source image editing APIs and demonstrate success rates of more than 88%. Our approach is simple, prompt-agnostic, and effective, offering a practical path towards protecting personal images from unauthorized AI-powered editing. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2606.26199 [cs.CR]   (or arXiv:2606.26199v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.26199 Focus to learn more Submission history From: Anshul Nasery [view email] [v1] Wed, 24 Jun 2026 16:23:10 UTC (44,098 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)