mlsanityData to 7 Oct 2026

Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples

arXiv 2302.04578 ↗First posted 9 Feb 2023cs.CV cs.AI cs.CRcited by 163

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

Abstract (arXiv)

Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style. To address these emerging copyright violations, in this paper, we are the first to explore and propose to utilize adversarial examples for DMs to protect human-created artworks. Specifically, we first build a theoretical framework to define and evaluate the adversarial examples for DMs. Then, based on this framework, we design a novel algorithm, named AdvDM, which exploits a Monte-Carlo estimation of adversarial examples for DMs by optimizing upon different latent variables sampled from the reverse process of DMs. Extensive experiments show that the generated adversarial examples can effectively hinder DMs from extracting their features. Therefore, our method can be a powerful tool for human artists to protect their copyright against infringers equipped with DM-based AI-for-Art applications. The code of our method is available on GitHub: https://github.com/mist-project/mist.git.

Key facts. Cited by 163 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 43 of its 66 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

43 of 66 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Diffusion Models for Adversarial Purification16 May

Other references · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  10. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  11. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  12. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
30 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  2. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  6. 2014Conditional Generative Adversarial Netscited by 2,152
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  9. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  10. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  11. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  12. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  13. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  14. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  15. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  16. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  17. 2017Countering Adversarial Images using Input Transformationscited by 517
  18. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  19. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  20. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  21. 2018Adversarial Attack on Graph Structured Datacited by 300
  22. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  23. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  24. 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
  25. 2019Image Super-Resolution as a Defense Against Adversarial Attackscited by 64
  26. 2017Adversarial examples for generative modelscited by 58
  27. 2016Towards Conceptual Compressioncited by 36
  28. 2021Copyright in Generative Deep Learningcited by 29
  29. 2019Understanding the Limitations of Conditional Generative Modelscited by 28
  30. 2019Adversarial Robustness of Flow-Based Generative Modelscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 25; 2024: 60; 2025: 48; 2026: 30.

163 papers.

Sort:

By area:

  1. 2023MMA-Diffusion: MultiModal Attack on Diffusion Modelscited by 184
  2. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesiscited by 114
  3. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 109
  4. 2023Mist: Towards Improved Adversarial Examples for Diffusion Modelscited by 91
  5. 2023Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Modelscited by 72
  6. 2023Toward effective protection against diffusion based mimicry through score distillationcited by 64
  7. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learningcited by 42
  8. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitationcited by 37
  9. 2023Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?cited by 37
  10. 2024Perception-guided Jailbreak against Text-to-Image Modelscited by 37
  11. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  12. 2023SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Modelscited by 34
38 more
  1. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  2. 2024On the Challenges and Opportunities in Generative AIcited by 31
  3. 2023EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Modelscited by 27
  4. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  5. 2024ADBM: Adversarial diffusion bridge model for reliable adversarial purificationcited by 24
  6. 2024Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Modelscited by 22
  7. 2023Generative Watermarking Against Unauthorized Subject-Driven Image Synthesiscited by 21
  8. 2024IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generationcited by 21
  9. 2023FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Modelscited by 20
  10. 2024A Survey on Diffusion Models for Recommender Systemscited by 20
  11. 2024Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editingcited by 19
  12. 2023DUAW: Data-free Universal Adversarial Watermark against Stable Diffusion Customizationcited by 18
  13. 2023Targeted Attack Improves Protection against Unauthorized Diffusion Customizationcited by 18
  14. 2024Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Modelscited by 18
  15. 2023IMMA: Immunizing text-to-image Models against Malicious Adaptationcited by 17
  16. 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policiescited by 17
  17. 2024Diffusion-Based Visual Art Creation: A Survey and New Perspectivescited by 17
  18. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  19. 2024Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Imagescited by 15
  20. 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Modelscited by 14
  21. 2024A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapsecited by 13
  22. 2024Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensicscited by 12
  23. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 12
  24. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  25. 2024Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Stepcited by 11
  26. 2025AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruptioncited by 11
  27. 2024Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Thinkcited by 10
  28. 2024Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Modelscited by 10
  29. 2024DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editingcited by 10
  30. 2024Dormant: Defending against Pose-driven Human Image Animationcited by 9
  31. 2024Text-to-Image Synthesis: A Decade Surveycited by 9
  32. 2025Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Modelscited by 9
  33. 2025AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editingcited by 9
  34. 2024Imperceptible Protection against Style Imitation from Diffusion Modelscited by 8
  35. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  36. 2024FaceShield: Defending Facial Image against Deepfake Threatscited by 8
  37. 2025PLA: Prompt Learning Attack against Text-to-Image Generative Modelscited by 8
  38. 2024Rethinking Impersonation and Dodging Attacks on Face Recognition Systemscited by 7

50 most cited of 163 All 163 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Adversarial Examples are Misaligned in Diffusion Model Manifolds
  2. 2023Measuring the Success of Diffusion Models at Imitating Human Artists
  3. 2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
  4. 2023My Art My Choice: Adversarial Protection Against Unruly AI
  5. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
  6. 2024Deceptive Diffusion: Generating Synthetic Adversarial Examples
  7. 2025Explore the vulnerability of black-box models via diffusion models
  8. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey