mlsanityData to 7 Oct 2026

Machine Unlearning for Image-to-Image Generative Models

arXiv 2402.00351 ↗First posted 1 Feb 2024cs.LG cs.CVcited by 47

On the map: LLM safety and security → Vision-language and text-to-image safety

Abstract (arXiv)

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification models, leaving the landscape of unlearning for generative models relatively unexplored. This paper serves as a bridge, addressing the gap by providing a unifying framework of machine unlearning for image-to-image generative models. Within this framework, we propose a computationally-efficient algorithm, underpinned by rigorous theoretical analysis, that demonstrates negligible performance degradation on the retain samples, while effectively removing the information from the forget samples. Empirical studies on two large-scale datasets, ImageNet-1K and Places-365, further show that our algorithm does not rely on the availability of the retain samples, which further complies with data retention policy. To our best knowledge, this work is the first that represents systemic, theoretical, empirical explorations of machine unlearning specifically tailored for image-to-image generative models. Our code is available at https://github.com/jpmorganchase/l2l-generator-unlearning.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security. Builds on 60 of its 77 references that are in the map. First posted on arXiv 1 Feb 2024.

Builds on

60 of 77 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Generative Adversarial Networks Unlearning19 Aug
  2. 2023Gradient Surgery for One-shot Unlearning on Generative Model10 Jul
  3. 2023Data Redaction from Conditional Generative Models18 May

Other references · 57

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  10. 2022Generative Adversarial Networkscited by 5,603
  11. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  12. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
38 more
  1. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2016Improved Techniques for Training GANscited by 2,938
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
  8. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  9. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  10. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  11. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  12. 2019Machine Unlearningcited by 1,020
  13. 2019An Introduction to Variational Autoencoderscited by 997
  14. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  15. 2023Extracting Training Data from Diffusion Modelscited by 723
  16. 2018MINE: Mutual Information Neural Estimationcited by 680
  17. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  18. 2019On Variational Bounds of Mutual Informationcited by 550
  19. 2023Erasing Concepts from Diffusion Modelscited by 530
  20. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  21. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  22. 2021GAN Inversion: A Surveycited by 366
  23. 2020Amnesiac Machine Learningcited by 305
  24. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  25. 2022A Survey of Machine Unlearningcited by 298
  26. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 278
  27. 2023Towards Unbounded Machine Unlearningcited by 261
  28. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 256
  29. 2021Machine Unlearning of Features and Labelscited by 223
  30. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 222
  31. 2022Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Modelscited by 218
  32. 2021Fast Yet Effective Machine Unlearningcited by 209
  33. 2021Autoregressive Diffusion Modelscited by 208
  34. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 180
  35. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 171
  36. 2023Boundary Unlearningcited by 132
  37. 2022Zero-Shot Machine Unlearningcited by 125
  38. 2018To learn image super-resolution, use a GAN to learn how to do image degradation firstcited by 94

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 17; 2025: 24; 2026: 6.

47 papers.

Sort:

By area:

  1. 2024SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearningcited by 104
  2. 2024Machine Unlearning in Generative AI: A Surveycited by 49
  3. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  4. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  5. 2024On Effects of Steering Latent Representation for Large Language Model Unlearningcited by 27
  6. 2024Pruning for Robust Concept Erasing in Diffusion Modelscited by 22
  7. 2024Learning to Unlearn for Robust Machine Unlearningcited by 19
  8. 2025Training-Free Safe Denoisers for Safe Use of Diffusion Modelscited by 19
  9. 2025Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearningcited by 19
  10. 2025Data Unlearning in Diffusion Modelscited by 18
  11. 2025Tool Unlearning for Tool-Augmented LLMscited by 17
  12. 2025LLM Unlearning with LLM Beliefscited by 17
35 more
  1. 2024MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearningcited by 16
  2. 2024Targeted Unlearning with Single Layer Unlearning Gradientcited by 16
  3. 2025Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocolscited by 16
  4. 2024Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Researchcited by 14
  5. 2024On the Limitations and Prospects of Machine Unlearning for Generative AIcited by 12
  6. 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivitycited by 11
  7. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  8. 2025UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targetscited by 10
  9. 2025Speech Unlearningcited by 7
  10. 2024Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classificationcited by 6
  11. 2025MUBox: A Critical Evaluation Framework of Deep Machine Unlearningcited by 6
  12. 2025Towards Source-Free Machine Unlearningcited by 6
  13. 2026Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarkscited by 6
  14. 2024Controllable Unlearning for Image-to-Image Generative Models via varepsilon-Constrained Optimizationcited by 5
  15. 2025"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understandingcited by 5
  16. 2025Unlearning Inversion Attacks for Graph Neural Networkscited by 4
  17. 2025Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocolscited by 4
  18. 2026The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samplescited by 4
  19. 2025Human Motion Unlearningcited by 3
  20. 2026An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representationscited by 3
  21. 2024Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstructioncited by 2
  22. 2024Accurate Forgetting for All-in-One Image Restoration Modelcited by 1
  23. 2025Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retentioncited by 1
  24. 2025RUB: Evaluating Residual Knowledge in Unlearned Modelscited by 1
  25. 2025SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Promptscited by 1
  26. 2025ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Modelscited by 1
  27. 2025Coffee: Controllable Diffusion Fine-tuningcited by 1
  28. 2025Erasing CLIP Memories: Non-Destructive, Data-Free Zero-Shot class Unlearning in CLIP Modelscited by 1
  29. 2025GenEAva: Generating Cartoon Avatars with Fine-Grained Facial Expressions from Realistic Diffusion-based Facescited by 0
  30. 2025Unleashing Uncertainty: Efficient Machine Unlearning for Generative AIcited by 0
  31. 2025Controllable Machine Unlearning via Gradient Pivotingcited by 0
  32. 2025Adaptive-lambda Subtracted Importance Sampled Scores in Machine Unlearning for DDPMs and VAEscited by 0
  33. 2026Efficient Unlearning through Maximizing Relearning Convergence Delaycited by 0
  34. 2026SoK: Unlearnability and Unlearning for Model Dememorizationcited by 0
  35. 2026To forget is to preserve: Machine Unlearning for 3D medical image segmentationcited by 0