mlsanityData to 7 Oct 2026

Mist: Towards Improved Adversarial Examples for Diffusion Models

arXiv 2305.12683 ↗First posted 22 May 2023cs.CV cs.AIcited by 91

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

Abstract (arXiv)

Diffusion Models (DMs) have empowered great success in artificial-intelligence-generated content, especially in artwork creation, yet raising new concerns in intellectual properties and copyright. For example, infringers can make profits by imitating non-authorized human-created paintings with DMs. Recent researches suggest that various adversarial examples for diffusion models can be effective tools against these copyright infringements. However, current adversarial examples show weakness in transferability over different painting-imitating methods and robustness under straightforward adversarial defense, for example, noise purification. We surprisingly find that the transferability of adversarial examples can be significantly enhanced by exploiting a fused and modified adversarial loss term under consistent parameters. In this work, we comprehensively evaluate the cross-method transferability of adversarial examples. The experimental observation shows that our method generates more transferable adversarial examples with even stronger robustness against the simple adversarial defense.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 12 of its 13 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

12 of 13 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesis27 Mar
  2. 2023Raising the Cost of Malicious AI-Powered Image Editing13 Feb
  3. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples9 Feb

Other references · 9

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  8. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  9. 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 200

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 28; 2025: 35; 2026: 22.

91 papers.

Sort:

By area:

  1. 2023Toward effective protection against diffusion based mimicry through score distillationcited by 64
  2. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learningcited by 42
  3. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  4. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  5. 2024Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Modelscited by 22
  6. 2023Targeted Attack Improves Protection against Unauthorized Diffusion Customizationcited by 18
  7. 2023IMMA: Immunizing text-to-image Models against Malicious Adaptationcited by 17
  8. 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policiescited by 17
  9. 2024A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapsecited by 13
  10. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 12
  11. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  12. 2025AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruptioncited by 11
38 more
  1. 2024Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Thinkcited by 10
  2. 2024DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editingcited by 10
  3. 2024Text-to-Image Synthesis: A Decade Surveycited by 9
  4. 2025AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editingcited by 9
  5. 2024Imperceptible Protection against Style Imitation from Diffusion Modelscited by 8
  6. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  7. 2024FaceShield: Defending Facial Image against Deepfake Threatscited by 8
  8. 2024U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AIcited by 7
  9. 2025TarPro: Targeted Protection against Malicious Image Editingcited by 7
  10. 2025DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editingcited by 7
  11. 2025StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbationscited by 7
  12. 2025Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generationcited by 7
  13. 2025Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezingcited by 7
  14. 2024PID: Prompt-Independent Data Protection Against Latent Diffusion Modelscited by 6
  15. 2024CopyrightMeter: Revisiting Copyright Protection in Text-to-image Modelscited by 6
  16. 2024Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Modelscited by 6
  17. 2025Enhancing Variational Autoencoders with Smooth Robust Latent Encodingcited by 6
  18. 2023VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Modelscited by 5
  19. 2024Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferabilitycited by 5
  20. 2025BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editingcited by 5
  21. 2025T2VAttack: Adversarial Attack on Text-to-Video Diffusion Modelscited by 5
  22. 2026Anti-I2V: Safeguarding your photos from malicious image-to-video generationcited by 5
  23. 2023A Somewhat Robust Image Watermark against Diffusion-based Editing Modelscited by 4
  24. 2024Multi-concept Model Immunization through Differentiable Model Mergingcited by 4
  25. 2025GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoorscited by 4
  26. 2025A Comprehensive Survey on Visual Concept Mining in Text-to-image Diffusion Modelscited by 4
  27. 2025Visual Watermarking in the Era of Diffusion Models: Advances and Challengescited by 4
  28. 2025My Face Is Mine, Not Yours: Facial Protection Against Diffusion Model Face Swappingcited by 4
  29. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
  30. 2025StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Modelscited by 4
  31. 2024Protect-Your-IP: Scalable Source-Tracing and Attribution against Personalized Generationcited by 3
  32. 2024DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Modelscited by 3
  33. 2025CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Modelscited by 3
  34. 2025Anti-Inpainting: A Proactive Defense Approach against Malicious Diffusion-based Inpainters under Unknown Conditionscited by 3
  35. 2025Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Studycited by 3
  36. 2025LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearningcited by 3
  37. 2025Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purificationcited by 3
  38. 2026Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generationcited by 3

50 most cited of 91 All 91 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Adversarial Examples are Misaligned in Diffusion Model Manifolds
  2. 2023Improving Adversarial Transferability by Stable Diffusion
  3. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
  4. 2023Adversarial defense based on distribution transfer
  5. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
  6. 2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
  7. 2023MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
  8. 2025Diffusion or Non-Diffusion Adversarial Defenses: Rethinking the Relation between Classifier and Adversarial Purifier