mlsanityData to 7 Oct 2026

Raising the Cost of Malicious AI-Powered Image Editing

arXiv 2302.06588 ↗First posted 13 Feb 2023cs.LGcited by 160

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

Abstract (arXiv)

We present an approach to mitigating the risks of malicious image editing posed by large diffusion models. The key idea is to immunize images so as to make them resistant to manipulation by these models. This immunization relies on injection of imperceptible adversarial perturbations designed to disrupt the operation of the targeted diffusion models, forcing them to generate unrealistic images. We provide two methods for crafting such perturbations, and then demonstrate their efficacy. Finally, we discuss a policy component necessary to make our approach fully effective and practical -- one that involves the organizations developing diffusion models, rather than individual users, to implement (and support) the immunization process.

Key facts. Cited by 160 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 41 of its 56 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

41 of 56 references.

References · 41

  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. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  10. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  11. 2016Improved Techniques for Training GANscited by 2,938
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
29 more
  1. 2014Conditional Generative Adversarial Netscited by 2,152
  2. 2016Adversarial examples in the physical worldcited by 1,762
  3. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  4. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  5. 2023A Watermark for Large Language Modelscited by 667
  6. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  7. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
  8. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  9. 2017Adversarial Patchcited by 514
  10. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  11. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  12. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  13. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
  14. 2018Assessing Generative Models via Precision and Recallcited by 401
  15. 2020The Creation and Detection of Deepfakes: A Surveycited by 246
  16. 2018DeepFakes: a New Threat to Face Recognition? Assessment and Detectioncited by 208
  17. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 193
  18. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
  19. 2018Physical Adversarial Examples for Object Detectorscited by 163
  20. 2018Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysiscited by 110
  21. 2019Unmasking DeepFakes with simple Featurescited by 78
  22. 2020Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systemscited by 65
  23. 2020Video Face Manipulation Detection Through Ensemble of CNNscited by 63
  24. 2016A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessmentcited by 57
  25. 2021Data Poisoning Won't Save You From Facial Recognitioncited by 45
  26. 2017Synthesizing Robust Adversarial Examplescited by 39
  27. 2021Adversarial Attacks Against Deep Generative Models on Data: A Surveycited by 23
  28. 2022FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakescited by 18
  29. 2020Protecting Against Image Translation Deepfakes by Leaking Universal Perturbations from Black-Box Neural Networkscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 30; 2024: 41; 2025: 49; 2026: 40.

160 papers.

Sort:

By area:

  1. 2023Erasing Concepts from Diffusion Modelscited by 530
  2. 2023Unified Concept Editing in Diffusion Modelscited by 377
  3. 2024MACE: Mass Concept Erasure in Diffusion Modelscited by 298
  4. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 281
  5. 2023MMA-Diffusion: MultiModal Attack on Diffusion Modelscited by 184
  6. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 105
  7. 2023Mist: Towards Improved Adversarial Examples for Diffusion Modelscited by 91
  8. 2023A Pilot Study of Query-Free Adversarial Attack against Stable Diffusioncited by 75
  9. 2023Content-based Unrestricted Adversarial Attackcited by 73
  10. 2023Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Modelscited by 72
  11. 2023Toward effective protection against diffusion based mimicry through score distillationcited by 64
  12. 2024Erasing Undesirable Influence in Diffusion Modelscited by 52
38 more
  1. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learningcited by 42
  2. 2024Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancycited by 38
  3. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitationcited by 37
  4. 2023Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?cited by 37
  5. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  6. 2023Watermarking Diffusion Modelcited by 34
  7. 2023SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Modelscited by 34
  8. 2023IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AIcited by 32
  9. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  10. 2023EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Modelscited by 27
  11. 2023Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noisecited by 23
  12. 2023Generative Watermarking Against Unauthorized Subject-Driven Image Synthesiscited by 21
  13. 2023On the Robustness of Latent Diffusion Modelscited by 21
  14. 2024IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generationcited by 21
  15. 2023FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Modelscited by 20
  16. 2024Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editingcited by 19
  17. 2023Targeted Attack Improves Protection against Unauthorized Diffusion Customizationcited by 18
  18. 2024Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Modelscited by 18
  19. 2023IMMA: Immunizing text-to-image Models against Malicious Adaptationcited by 17
  20. 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policiescited by 17
  21. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  22. 2024Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Imagescited by 15
  23. 2023JPEG Compressed Images Can Bypass Protections Against AI Editingcited by 14
  24. 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Modelscited by 14
  25. 2024A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapsecited by 13
  26. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 12
  27. 2025AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruptioncited by 11
  28. 2024Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Thinkcited by 10
  29. 2024DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editingcited by 10
  30. 2024PRIME: Protect Your Videos From Malicious Editingcited by 9
  31. 2024JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Editscited by 9
  32. 2024Dormant: Defending against Pose-driven Human Image Animationcited by 9
  33. 2025Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Modelscited by 9
  34. 2025AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editingcited by 9
  35. 2024Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Maskingcited by 8
  36. 2024Imperceptible Protection against Style Imitation from Diffusion Modelscited by 8
  37. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  38. 2024Disrupting Diffusion-based Inpainters with Semantic Digressioncited by 8

50 most cited of 160 All 160 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors
  2. 2026SPIN: Image Immunization Against Diffusion Editing via Single-Step Projection in Stochastic Neighborhoods
  3. 2025GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention
  4. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
  5. 2024Deceptive Diffusion: Generating Synthetic Adversarial Examples
  6. 2026Anti-I2V: Safeguarding your photos from malicious image-to-video generation
  7. 2025SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts
  8. 2025Make the Most of Everything: Further Considerations on Disrupting Diffusion-based Customization