mlsanityData to 14 Oct 2026

Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers

arXiv 2311.17717 ↗First posted 29 Nov 2023cs.CV cs.LGcited by 120

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

Abstract (arXiv)

Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable. The former refrains the model from producing images associated with the target concept for any paraphrased or learned prompts, while the latter preserves its ability in generating images with non-target concepts. In this paper, we propose Reliable Concept Erasing via Lightweight Erasers (Receler). It learns a lightweight Eraser to perform concept erasing while satisfying the above desirable properties through the proposed concept-localized regularization and adversarial prompt learning scheme. Experiments with various concepts verify the superiority of Receler over previous methods.

Key facts. Cited by 120 papers in the map (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 47 of its 57 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

47 of 57 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now18 Oct
  2. 2023Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?16 Oct
  3. 2023Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts12 Sep
  4. 2023Unified Concept Editing in Diffusion Models25 Aug
  5. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models30 Mar
  6. 2023Ablating Concepts in Text-to-Image Diffusion Models23 Mar
  7. 2023Erasing Concepts from Diffusion Models13 Mar
  8. 2023Extracting Training Data from Diffusion Models30 Jan
  9. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models9 Nov

Other references · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  11. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  12. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
26 more
  1. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  2. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  3. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  4. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  5. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  8. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  9. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  10. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  11. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  12. 2021Editing Factual Knowledge in Language Modelscited by 553
  13. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  14. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 379
  15. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 372
  16. 2023Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Modelscited by 359
  17. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  18. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 236
  19. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMscited by 215
  20. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 197
  21. 2020Editable Neural Networkscited by 155
  22. 2022Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?cited by 155
  23. 2022The Privacy Onion Effect: Memorization is Relativecited by 136
  24. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  25. 2023A Closer Look at Parameter-Efficient Tuning in Diffusion Modelscited by 15
  26. 2023ORES: Open-vocabulary Responsible Visual Synthesiscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 29; 2025: 50; 2026: 41.

120 papers.

Sort:

By area:

  1. 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Modelscited by 168
  2. 2024SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generationcited by 133
  3. 2024EraseAnything: Enabling Concept Erasure in Rectified Flow Transformerscited by 95
  4. 2025Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Conceptscited by 62
  5. 2024R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Modelcited by 58
  6. 2024ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruningcited by 55
  7. 2024UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Modelscited by 50
  8. 2024Machine Unlearning in Generative AI: A Surveycited by 49
  9. 2024STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Modelscited by 42
  10. 2024Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Conceptscited by 40
  11. 2025SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Modelscited by 36
  12. 2024ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Userscited by 35
38 more
  1. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Surveycited by 35
  2. 2025Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptationcited by 33
  3. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  4. 2024Jailbreak Attacks and Defenses against Multimodal Generative Models: A Surveycited by 32
  5. 2024Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearningcited by 29
  6. 2024Separable Multi-Concept Erasure from Diffusion Modelscited by 28
  7. 2025CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Modelscited by 27
  8. 2024TraSCE: Trajectory Steering for Concept Erasurecited by 26
  9. 2025Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Modelscited by 25
  10. 2024Data Attribution for Text-to-Image Models by Unlearning Synthesized Imagescited by 22
  11. 2024Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearningcited by 21
  12. 2025VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Modelscited by 17
  13. 2024Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Modelscited by 16
  14. 2025One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Frameworkcited by 16
  15. 2025T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Modelscited by 16
  16. 2025Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gatecited by 16
  17. 2024Espresso: Robust Concept Filtering in Text-to-Image Modelscited by 14
  18. 2026Mass Concept Erasure in Diffusion Models with Concept Hierarchycited by 14
  19. 2025Side Effects of Erasing Concepts from Diffusion Modelscited by 13
  20. 2025Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Conceptscited by 12
  21. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  22. 2025DuMo: Dual Encoder Modulation Network for Precise Concept Erasurecited by 11
  23. 2025Concept Corrector: Erase concepts on the fly for text-to-image diffusion modelscited by 11
  24. 2024SteerDiff: Steering towards Safe Text-to-Image Diffusion Modelscited by 10
  25. 2025Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppressioncited by 10
  26. 2025Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearningcited by 10
  27. 2025SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoderscited by 10
  28. 2024Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policycited by 9
  29. 2025A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Modelscited by 9
  30. 2025Erased but Not Forgotten: How Backdoors Compromise Concept Erasurecited by 9
  31. 2025Erased or Dormant? Rethinking Concept Erasure Through Reversibilitycited by 9
  32. 2025Rethinking Machine Unlearning in Image Generation Modelscited by 9
  33. 2025Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuningcited by 9
  34. 2025EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignmentcited by 9
  35. 2025CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabularycited by 8
  36. 2025Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Modelscited by 8
  37. 2025Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Modelscited by 8
  38. 2024AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchorscited by 7

50 most cited of 120 All 120 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
  2. 2026Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
  3. 2026Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
  4. 2024Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
  5. 2024Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
  6. 2025Rethinking the Vulnerability of Concept Erasure and a New Method
  7. 2026Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information
  8. 2023All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models