mlsanityData to 7 Oct 2026

VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models

arXiv 2312.00057 ↗First posted 29 Nov 2023cs.CR cs.AI cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

The booming use of text-to-image generative models has raised concerns about their high risk of producing copyright-infringing content. While probabilistic copyright protection methods provide a probabilistic guarantee against such infringement, in this paper, we introduce Virtually Assured Amplification Attack (VA3), a novel online attack framework that exposes the vulnerabilities of these protection mechanisms. The proposed framework significantly amplifies the probability of generating infringing content on the sustained interactions with generative models and a non-trivial lower-bound on the success probability of each engagement. Our theoretical and experimental results demonstrate the effectiveness of our approach under various scenarios. These findings highlight the potential risk of implementing probabilistic copyright protection in practical applications of text-to-image generative models. Code is available at https://github.com/South7X/VA3.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 51 of its 61 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

51 of 61 references.

References · 51

  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. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  10. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  11. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
38 more
  1. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  2. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  3. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  4. 2023Extracting Training Data from Diffusion Modelscited by 723
  5. 2023Erasing Concepts from Diffusion Modelscited by 530
  6. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 501
  7. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  8. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  9. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 312
  10. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 297
  11. 2022Red-Teaming the Stable Diffusion Safety Filtercited by 257
  12. 2023Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?cited by 239
  13. 2023Understanding and Mitigating Copying in Diffusion Modelscited by 205
  14. 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 200
  15. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robustcited by 179
  16. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  17. 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Modelscited by 171
  18. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examplescited by 163
  19. 2023Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Promptscited by 161
  20. 2023Raising the Cost of Malicious AI-Powered Image Editingcited by 160
  21. 2023Cones: Concept Neurons in Diffusion Models for Customized Generationcited by 150
  22. 2023A Recipe for Watermarking Diffusion Modelscited by 136
  23. 2023Foundation Models and Fair Usecited by 112
  24. 2022How to Backdoor Diffusion Models?cited by 102
  25. 2023On Provable Copyright Protection for Generative Modelscited by 97
  26. 2023How Does Information Bottleneck Help Deep Learning?cited by 92
  27. 2023Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoningcited by 91
  28. 2023Mist: Towards Improved Adversarial Examples for Diffusion Modelscited by 91
  29. 2023TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targetscited by 88
  30. 2023A Pilot Study of Query-Free Adversarial Attack against Stable Diffusioncited by 75
  31. 2023DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Modelscited by 41
  32. 2023Towards More Realistic Membership Inference Attacks on Large Diffusion Modelscited by 41
  33. 2023Can Copyright be Reduced to Privacy?cited by 24
  34. 2023Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attackscited by 24
  35. 2023DUAW: Data-free Universal Adversarial Watermark against Stable Diffusion Customizationcited by 18
  36. 2022Formalizing Human Ingenuity: A Quantitative Framework for Copyright Law's Substantial Similaritycited by 15
  37. 2023On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Promptscited by 14
  38. 2023Measuring the Success of Diffusion Models at Imitating Human Artistscited by 10

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 3.

5 papers.

  1. 2024Jailbreak Attacks and Defenses against Multimodal Generative Models: A Surveycited by 31
  2. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  3. 2025Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Modelscited by 3
  4. 2025ME: Trigger Element Combination Backdoor Attack on Copyright Infringementcited by 2
  5. 2025Blameless Users in a Clean Room: Defining Copyright Protection for Generative Modelscited by 1