mlsanityData to 14 Oct 2026

Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models

arXiv 2305.10120 ↗First posted 17 May 2023cs.LG cs.AIcited by 177

Not on the map. Why?

Cited by 104 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by continual learning to selectively forget concepts in pretrained deep generative models. Our method, dubbed Selective Amnesia, enables controllable forgetting where a user can specify how a concept should be forgotten. Selective Amnesia can be applied to conditional variational likelihood models, which encompass a variety of popular deep generative frameworks, including variational autoencoders and large-scale text-to-image diffusion models. Experiments across different models demonstrate that our approach induces forgetting on a variety of concepts, from entire classes in standard datasets to celebrity and nudity prompts in text-to-image models. Our code is publicly available at https://github.com/clear-nus/selective-amnesia.

Key facts. Cited by 177 papers in the map (data through 14 Oct 2026). Builds on 29 of its 36 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

29 of 36 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  10. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  11. 2016Progressive Neural Networkscited by 1,361
  12. 2017Continual Learning with Deep Generative Replaycited by 1,158
17 more
  1. 2019Machine Unlearningcited by 1,061
  2. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  3. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  4. 2023Erasing Concepts from Diffusion Modelscited by 539
  5. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 513
  6. 2018Assessing Generative Models via Precision and Recallcited by 406
  7. 2017Variational Continual Learningcited by 339
  8. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 301
  9. 2020The Creation and Detection of Deepfakes: A Surveycited by 247
  10. 2020Media Forensics and DeepFakes: an overviewcited by 209
  11. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 149
  12. 2020Variational Bayesian Unlearningcited by 117
  13. 2020Rewriting a Deep Generative Modelcited by 107
  14. 2018Generative Models from the perspective of Continual Learningcited by 69
  15. 2017Continual Learning in Generative Adversarial Netscited by 51
  16. 2016Neurogenesis Deep Learningcited by 32
  17. 2022Data Redaction from Pre-trained GANscited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 15; 2024: 54; 2025: 61; 2026: 47.

177 papers.

Sort:

By area:

  1. 2023Unified Concept Editing in Diffusion Modelscited by 388
  2. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 386
  3. 2024MACE: Mass Concept Erasure in Diffusion Modelscited by 307
  4. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Nowcited by 210
  5. 2023One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applicationscited by 169
  6. 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Modelscited by 168
  7. 2023Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attackscited by 158
  8. 2023Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Modelscited by 153
  9. 2024Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Modelscited by 133
  10. 2024SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generationcited by 133
  11. 2023Circumventing Concept Erasure Methods For Text-to-Image Generative Modelscited by 85
  12. 2025SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoderscited by 80
38 more
  1. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 69
  2. 2023Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generationcited by 69
  3. 2025Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Conceptscited by 62
  4. 2024R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Modelcited by 58
  5. 2024Erasing Undesirable Influence in Diffusion Modelscited by 57
  6. 2024ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruningcited by 55
  7. 2024Scissorhands: Scrub Data Influence via Connection Sensitivity in Networkscited by 52
  8. 2024UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Modelscited by 50
  9. 2024Direct Unlearning Optimization for Robust and Safe Text-to-Image Modelscited by 50
  10. 2024Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancementcited by 45
  11. 2024Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearningcited by 44
  12. 2024STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Modelscited by 42
  13. 2024Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Conceptscited by 40
  14. 2024Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matterscited by 40
  15. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Surveycited by 35
  16. 2024Erasing Conceptual Knowledge from Language Modelscited by 34
  17. 2025Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptationcited by 33
  18. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  19. 2024Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearningcited by 29
  20. 2024Dynamic Negative Guidance of Diffusion Modelscited by 28
  21. 2024Robust Concept Erasure Using Task Vectorscited by 27
  22. 2025CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Modelscited by 27
  23. 2024TraSCE: Trajectory Steering for Concept Erasurecited by 26
  24. 2024Cross-Modal Safety Alignment: Is textual unlearning all you need?cited by 25
  25. 2024Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidancecited by 24
  26. 2024Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Modelscited by 23
  27. 2024Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearningcited by 21
  28. 2025Training-Free Safe Denoisers for Safe Use of Diffusion Modelscited by 21
  29. 2024Learning to Unlearn for Robust Machine Unlearningcited by 19
  30. 2025Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearningcited by 19
  31. 2025Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimizationcited by 19
  32. 2023IMMA: Immunizing text-to-image Models against Malicious Adaptationcited by 18
  33. 2025Data Unlearning in Diffusion Modelscited by 18
  34. 2024MUNBa: Machine Unlearning via Nash Bargainingcited by 17
  35. 2024Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Modelscited by 16
  36. 2025One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Frameworkcited by 16
  37. 2025When Are Concepts Erased From Diffusion Models?cited by 16
  38. 2025Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gatecited by 16

50 most cited of 177 All 177 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
  2. 2025Mitigating Catastrophic Forgetting and Mode Collapse in Text-to-Image Diffusion via Latent Replay
  3. 2026Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
  4. 2025Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
  5. 2025Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized
  6. 2024CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning
  7. 2025Deep Generative Continual Learning using Functional LoRA: FunLoRA
  8. 2024Caption, Create, Continue: Continual Learning with Pre-trained Generative Vision-Language Models