Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation

• URL: http://arxiv.org/abs/2605.22060v1
• Date: Thu, 21 May 2026 06:50:50 GMT
• Title: Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation
• Abstract summary: We present WaveGuard, a single-pass, generator-based protection framework for closed-weight generative services.<n>WaveGuard safeguards released synthetic images under a user-specified perturbation budget.
• Score: 49.23010932057819
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Closed-weight generative services are increasingly deployed through query-based APIs, where users can obtain generated outputs while model parameters remain inaccessible. However, such deployment does not prevent model stealing: an attacker can repeatedly query the service, collect large volumes of released synthetic images, and use them as training data for a private substitute model. This query-output-driven process enables unauthorized knowledge distillation and capability replication without direct access to the original weights. To mitigate this threat, a practical defense should preserve the visual fidelity of released images, provide explicit control over perturbation magnitude, and scale efficiently to large-volume output release. We present WaveGuard, a single-pass, generator-based protection framework that safeguards released synthetic images under a user-specified perturbation budget. WaveGuard employs a frequency-aware perturbation generator to inject structured, imperceptible perturbations that maintain perceptual utility for benign viewers while reducing the usefulness of protected images as training data for unauthorized student models. Extensive experiments under WikiArt-related synthetic-output distillation settings show that WaveGuard achieves a favorable efficacy--fidelity--efficiency trade-off, with explicit imperceptibility control and substantial gains in protection efficiency.

Related papers

• Reversible Unlearnable Examples: Towards the Copyright Protection in Deep Learning Era [11.78038647588361]
  Copyright protection in deep learning faces two main threats: illegal model training and malicious data leakage.<n>We propose a novel copyright protection mechanism for the aforementioned security concerns.<n>Our proposed method could provide comprehensive copyright protection to images.
  arXiv  Detail & Related papers  (2026-08-06T16:04:05Z)
• Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization [51.33055188976282]
  adversarial attacks have emerged as a prominent defense strategy to prevent malicious content forgery in personalized image generation.<n>We introduce Two-Stage Latent Feature Optimization (TS-LFO), an efficient and effective copyright-stealing attack against protected diffusion-based customization.<n>Extensive experiments show that TS-LFO consistently bypasses state-of-the-art (SOTA) copyright defenses and outperforms SOTA copyright attacks such as DiffPure, GrIDPure and IMPRESS.
  arXiv  Detail & Related papers  (2026-06-06T07:59:08Z)
• Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch [21.826849937304477]
  Diffusion models enable high-fidelity image editing but can also be misused for unauthorized style imitation and harmful content generation.<n>To mitigate these risks, proactive image protection methods embed small, often imperceptible adversarial perturbations into images before sharing to disrupt downstream editing or fine-tuning.<n>We introduce a unified post-release purification framework to evaluate protection survivability under model mismatch.
  arXiv  Detail & Related papers  (2026-03-13T14:36:46Z)
• AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing [109.07334219188222]
  We propose the first editing safeguard for 3DGS, termed AdLift, which prevents instruction-driven editing across arbitrary views and dimensions.<n>We alternate between gradient truncation and image-to-Gaussian fitting, yielding consistent adversarial-based protection performance across different viewpoints.
  arXiv  Detail & Related papers  (2025-12-08T07:41:23Z)
• 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)
• Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models [26.821064889438777]
  We present novel evidence that diffusion-generated images faithfully preserve the statistical properties of their training data.<n>We introduce emphCoprGuard, a robust frequency domain watermarking framework to safeguard against unauthorized image usage.
  arXiv  Detail & Related papers  (2025-03-14T04:27:50Z)
• 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)
• PersGuard: Preventing Malicious Personalization via Backdoor Attacks on Pre-trained Text-to-Image Diffusion Models [51.458089902581456]
  We introduce PersGuard, a novel backdoor-based approach that prevents malicious personalization of specific images.<n>Our method significantly outperforms existing techniques, offering a more robust solution for privacy and copyright protection.
  arXiv  Detail & Related papers  (2025-02-22T09:47:55Z)
• EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations [73.94175015918059]
  We introduce a novel approach, EnTruth, which Enhances Traceability of unauthorized dataset usage. By strategically incorporating the template memorization, EnTruth can trigger the specific behavior in unauthorized models as the evidence of infringement. Our method is the first to investigate the positive application of memorization and use it for copyright protection, which turns a curse into a blessing.
  arXiv  Detail & Related papers  (2024-06-20T02:02:44Z)
• 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)
• Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation [25.55296442023984]
  We propose a method, Unlearnable Diffusion Perturbation, to safeguard images from unauthorized exploitation. This achievement holds significant importance in real-world scenarios, as it contributes to the protection of privacy and copyright against AI-generated content.
  arXiv  Detail & Related papers  (2023-06-02T20:19:19Z)

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.