mlsanityData to 14 Oct 2026

Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation

arXiv 2412.18791 ↗First posted 25 Dec 2024cs.CVcited by 2

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

Diffusion-based text-to-image models have shown immense potential for various image-related tasks. However, despite their prominence and popularity, customizing these models using unauthorized data also brings serious privacy and intellectual property issues. Existing methods introduce protective perturbations based on adversarial attacks, which are applied to the customization samples. In this systematization of knowledge, we present a comprehensive survey of protective perturbation methods designed to prevent unauthorized data usage in diffusion-based image generation. We establish the threat model and categorize the downstream tasks relevant to these methods, providing a detailed analysis of their designs. We also propose a completed evaluation framework for these perturbation techniques, aiming to advance research in this field.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 30 of its 36 references that are in the map. First posted on arXiv 25 Dec 2024.

Builds on

30 of 36 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse20 Aug
  2. 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models20 Aug
  3. 2024Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability13 Jan
  4. 2023SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models13 Dec
  5. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning22 Nov
  6. 2023IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI30 Oct
  7. 2023Toward effective protection against diffusion based mimicry through score distillation2 Oct
  8. 2023On the Robustness of Latent Diffusion Models14 Jun
  9. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation2 Jun
  10. 2023Mist: Towards Improved Adversarial Examples for Diffusion Models22 May
  11. 2023JPEG Compressed Images Can Bypass Protections Against AI Editing5 Apr
  12. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesis27 Mar
2 more
  1. 2023Raising the Cost of Malicious AI-Powered Image Editing13 Feb
  2. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples9 Feb

Other references · 16

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2023Segment Anythingcited by 8,234
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  10. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  11. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  12. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
4 more
  1. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  2. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  3. 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 205
  4. 2023Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Modelscited by 75

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Modelscited by 4
  2. 2026A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalitiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Study
  2. 2023Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
  3. 2023Targeted Attack Improves Protection against Unauthorized Diffusion Customization
  4. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
  5. 2024DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
  6. 2025Is Perturbation-Based Image Protection Disruptive to Image Editing?
  7. 2025Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
  8. 2025PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors