mlsanityData to 7 Oct 2026

Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models

arXiv 2302.04222 ↗First posted 8 Feb 2023cs.CRcited by 200

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Recent text-to-image diffusion models such as MidJourney and Stable Diffusion threaten to displace many in the professional artist community. In particular, models can learn to mimic the artistic style of specific artists after "fine-tuning" on samples of their art. In this paper, we describe the design, implementation and evaluation of Glaze, a tool that enables artists to apply "style cloaks" to their art before sharing online. These cloaks apply barely perceptible perturbations to images, and when used as training data, mislead generative models that try to mimic a specific artist. In coordination with the professional artist community, we deploy user studies to more than 1000 artists, assessing their views of AI art, as well as the efficacy of our tool, its usability and tolerability of perturbations, and robustness across different scenarios and against adaptive countermeasures. Both surveyed artists and empirical CLIP-based scores show that even at low perturbation levels (p=0.05), Glaze is highly successful at disrupting mimicry under normal conditions (>92%) and against adaptive countermeasures (>85%).

Key facts. Cited by 200 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 54 of its 127 references that are in the map. First posted on arXiv 8 Feb 2023.

Builds on

54 of 127 references.

Closest ancestors · 6

Same direction, newest first

  1. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2 Nov
  2. 2022Imagic: Text-Based Real Image Editing with Diffusion Models17 Oct
  3. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  6. 2021Palette: Image-to-Image Diffusion Models10 Nov

Other references · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  6. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  9. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  11. 2016Adversarial examples in the physical worldcited by 1,762
  12. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
36 more
  1. 2014How transferable are features in deep neural networks?cited by 1,216
  2. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2022On Distillation of Guided Diffusion Modelscited by 721
  5. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
  6. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  7. 2017The Perception-Distortion Tradeoffcited by 582
  8. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  9. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  10. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  11. 2020Understanding the Behaviour of Contrastive Losscited by 397
  12. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  13. 2022Scaling Language-Image Pre-training via Maskingcited by 317
  14. 2019DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesiscited by 308
  15. 2017Detecting Adversarial Samples from Artifactscited by 244
  16. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  17. 2022Re-Imagen: Retrieval-Augmented Text-to-Image Generatorcited by 208
  18. 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 181
  19. 2020DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesiscited by 161
  20. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  21. 2015Generating Images from Captions with Attentioncited by 135
  22. 2019Object-driven Text-to-Image Synthesis via Adversarial Trainingcited by 117
  23. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
  24. 2016Deep Feature Interpolation for Image Content Changescited by 80
  25. 2018Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attackscited by 78
  26. 2017Adversarial examples for generative modelscited by 58
  27. 2015Adversarial Manipulation of Deep Representationscited by 56
  28. 2021Data Poisoning Won't Save You From Facial Recognitioncited by 45
  29. 2019Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networkscited by 40
  30. 2020Augmented Lagrangian Adversarial Attackscited by 28
  31. 2020ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detectioncited by 27
  32. 2020Face-Off: Adversarial Face Obfuscationcited by 25
  33. 2016Adversarial Images for Variational Autoencoderscited by 19
  34. 2018Adversarial Attacks on Variational Autoencoderscited by 19
  35. 2020FoggySight: A Scheme for Facial Lookup Privacycited by 12
  36. 2022Post-breach Recovery: Protection against White-box Adversarial Examples for Leaked DNN Modelscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 45; 2024: 73; 2025: 47; 2026: 35.

200 papers.

Sort:

By area:

  1. 2023Erasing Concepts from Diffusion Modelscited by 530
  2. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  3. 2023Unified Concept Editing in Diffusion Modelscited by 377
  4. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 312
  5. 2024MACE: Mass Concept Erasure in Diffusion Modelscited by 298
  6. 2023Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Modelscited by 203
  7. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesiscited by 114
  8. 2023Art and the science of generative AI: A deeper divecited by 93
  9. 2023Mist: Towards Improved Adversarial Examples for Diffusion Modelscited by 91
  10. 2023Evaluating the Social Impact of Generative AI Systems in Systems and Societycited by 91
  11. 2023Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Modelscited by 72
  12. 2023Toward effective protection against diffusion based mimicry through score distillationcited by 64
38 more
  1. 2024Erasing Undesirable Influence in Diffusion Modelscited by 52
  2. 2023Prompt Stealing Attacks Against Text-to-Image Generation Modelscited by 48
  3. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimizationcited by 45
  4. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learningcited by 42
  5. 2024Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancycited by 38
  6. 2024Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matterscited by 38
  7. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitationcited by 37
  8. 2023Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?cited by 37
  9. 2023Black-box Membership Inference Attacks against Fine-tuned Diffusion Modelscited by 35
  10. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  11. 2023SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Modelscited by 34
  12. 2025SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Modelscited by 33
  13. 2023IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AIcited by 32
  14. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  15. 2025Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Taskscited by 28
  16. 2023EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Modelscited by 27
  17. 2024Separable Multi-Concept Erasure from Diffusion Modelscited by 25
  18. 2024CPR: Retrieval Augmented Generation for Copyright Protectioncited by 22
  19. 2024Automatic Jailbreaking of the Text-to-Image Generative AI Systemscited by 22
  20. 2024Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Modelscited by 22
  21. 2023Generative Watermarking Against Unauthorized Subject-Driven Image Synthesiscited by 21
  22. 2024Organic or Diffused: Can We Distinguish Human Art from AI-generated Images?cited by 21
  23. 2024IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generationcited by 21
  24. 2023FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Modelscited by 20
  25. 2023The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Modelscited by 19
  26. 2024Generative Unlearning for Any Identitycited by 19
  27. 2024Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Modelscited by 19
  28. 2024Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editingcited by 19
  29. 2023DUAW: Data-free Universal Adversarial Watermark against Stable Diffusion Customizationcited by 18
  30. 2023Targeted Attack Improves Protection against Unauthorized Diffusion Customizationcited by 18
  31. 2024An Economic Solution to Copyright Challenges of Generative AIcited by 18
  32. 2024Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Modelscited by 18
  33. 2023IMMA: Immunizing text-to-image Models against Malicious Adaptationcited by 17
  34. 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policiescited by 17
  35. 2024CDI: Copyrighted Data Identification in Diffusion Modelscited by 17
  36. 2025Rethinking Data Protection in the (Generative) Artificial Intelligence Eracited by 17
  37. 2023Training Data Protection with Compositional Diffusion Modelscited by 16
  38. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15

50 most cited of 200 All 200 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models
  2. 2023Measuring the Success of Diffusion Models at Imitating Human Artists
  3. 2026Through Van Gogh's Eyes: Global Style Transfer with Diffusion Model
  4. 2025The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models
  5. 2024Learning Artistic Signatures: Symmetry Discovery and Style Transfer
  6. 2023Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis
  7. 2025Style Transfer: A Decade Survey
  8. 2024KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models