MIRAGE: Protecting against Malicious Image Editing via False Moderation

• URL: http://arxiv.org/abs/2606.26199v2
• Date: Fri, 26 Jun 2026 02:47:28 GMT
• Title: MIRAGE: Protecting against Malicious Image Editing via False Moderation
• Abstract summary: Prior work on image immunization adds imperceptible perturbations to an image to protect against unauthorized manipulations.<n>We take a system-level view of the problem and identify a previously unexplored attack surface common to all major commercial image editing systems.<n>We propose to immunize images by causing these moderations to flag images as policy-violating, triggering an automatic refusal regardless of the editing prompt.
• Score: 73.0838743416626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 moderation. Rather 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.

Related papers

• Towards Transferable Defense Against Malicious Image Edits [70.17363183107604]
  Transferable Defense Against Malicious Image Edits (TDAE) is a novel bimodal framework that enhances image immunity against malicious edits.<n>We introduce FlatGrad Defense Mechanism (FDM), which incorporates gradient regularization into the adversarial objective.<n>For textual enhancement protection, we propose Dynamic Prompt Defense (DPD), which periodically refines text embeddings to align the editing outcomes of immunized images with those of the original images.
  arXiv  Detail & Related papers  (2025-12-16T12:10:16Z)
• Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation [74.5813283875938]
  Zero-shot image-to-image generation poses substantial risks related to intellectual property violations.<n>This work presents Adapter Shield, the first universal and authentication-integrated solution aimed at defending personal images from misuse.<n>Our method surpasses existing state-of-the-art defenses in blocking unauthorized zero-shot image synthesis.
  arXiv  Detail & Related papers  (2025-11-25T04:49:16Z)
• Is Perturbation-Based Image Protection Disruptive to Image Editing? [4.234664611250363]
  Current image protection methods rely on adding imperceptible perturbations to images to obstruct diffusion-based editing.<n>A fully successful protection for an image implies that the output of editing attempts is an undesirable, noisy image.<n>We argue that perturbation-based methods may not provide a sufficient solution for robust image protection against diffusion-based editing.
  arXiv  Detail & Related papers  (2025-06-04T19:20:37Z)
• DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editing [1.7624347338410742]
  Recent defenses attempt to protect images by adding a limited noise in the pixel space to disrupt the functioning of diffusion-based editing models.<n>We propose a novel optimization approach that introduces adversarial perturbations directly in the frequency domain.<n>By leveraging the JPEG pipeline, our method generates adversarial images that effectively prevent malicious image editing.
  arXiv  Detail & Related papers  (2025-04-24T19:14:50Z)
• GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors [8.261182037130407]
  GuardDoor is a novel and robust protection mechanism that fosters collaboration between image owners and model providers.<n>Our method demonstrates enhanced robustness against image preprocessing operations and is scalable for large-scale deployment.
  arXiv  Detail & Related papers  (2025-03-05T22:21:44Z)
• ACE: Anti-Editing Concept Erasure in Text-to-Image Models [73.00930293474009]
  Existing concept erasure methods achieve superior results in preventing the production of erased concept from prompts.<n>We propose an Anti-Editing Concept Erasure (ACE) method, which not only erases the target concept during generation but also filters out it during editing.
  arXiv  Detail & Related papers  (2025-01-03T04:57:27Z)
• IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI [52.90082445349903]
  Diffusion-based image generation models can create artistic images that mimic the style of an artist or maliciously edit the original images for fake content. Several attempts have been made to protect the original images from such unauthorized data usage by adding imperceptible perturbations. In this work, we introduce a purification perturbation platform, named IMPRESS, to evaluate the effectiveness of imperceptible perturbations as a protective measure.
  arXiv  Detail & Related papers  (2023-10-30T03:33:41Z)
• JPEG Compressed Images Can Bypass Protections Against AI Editing [48.340067730457584]
  Imperceptible perturbations have been proposed as a means of protecting images from malicious editing. We find that the aforementioned perturbations are not robust to JPEG compression.
  arXiv  Detail & Related papers  (2023-04-05T05:30:09Z)
• TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations [0.0]
  Face image manipulation methods can raise concerns by affecting an individual's privacy or spreading disinformation. In this work, we propose a proactive defense to prevent face manipulation from happening in the first place. We introduce a novel data-driven approach that produces image-specific perturbations which are embedded in the original images.
  arXiv  Detail & Related papers  (2021-12-16T19:00:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.