# Model Integrity when Unlearning with T2I Diffusion Models

arXiv: https://arxiv.org/abs/2411.02068 · HTML: https://mlsanity.com/paper/2411.02068/

## Key facts

- Cited by 7 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 23 of its 33 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 23 of 23)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models](https://mlsanity.com/paper/2305.10120/) (2023)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications](https://mlsanity.com/paper/2312.16145/) (2023)
- [Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2405.15234/) (2024)
- [Circumventing Concept Erasure Methods For Text-to-Image Generative Models](https://mlsanity.com/paper/2308.01508/) (2023)
- [Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient](https://mlsanity.com/paper/2405.15304/) (2024)
- [Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2402.05375/) (2024)
- [Erasing Undesirable Influence in Diffusion Models](https://mlsanity.com/paper/2401.05779/) (2024)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)

## Built on by (most cited first, 7 of 7)

- [Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts](https://mlsanity.com/paper/2504.12782/) (2025)
- [Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks](https://mlsanity.com/paper/2607.07907/) (2026)
- [ACE: Attentional Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2504.11850/) (2025)
- [Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2502.16708/) (2025)
- [Selective Fine-Tuning for Targeted and Robust Concept Unlearning](https://mlsanity.com/paper/2602.07919/) (2026)
- [You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2603.00133/) (2026)
- [Why Instruction-Based Unlearning Fails in Diffusion Models?](https://mlsanity.com/paper/2604.01514/) (2026)

## Abstract (arXiv)

The rapid advancement of text-to-image Diffusion Models has led to their widespread public accessibility. However these models, trained on large internet datasets, can sometimes generate undesirable outputs. To mitigate this, approximate Machine Unlearning algorithms have been proposed to modify model weights to reduce the generation of specific types of images, characterized by samples from a ``forget distribution'', while preserving the model's ability to generate other images, characterized by samples from a ``retain distribution''. While these methods aim to minimize the influence of training data in the forget distribution without extensive additional computation, we point out that they can compromise the model's integrity by inadvertently affecting generation for images in the retain distribution. Recognizing the limitations of FID and CLIPScore in capturing these effects, we introduce a novel retention metric that directly assesses the perceptual difference between outputs generated by the original and the unlearned models. We then propose unlearning algorithms that demonstrate superior effectiveness in preserving model integrity compared to existing baselines. Given their straightforward implementation, these algorithms serve as valuable benchmarks for future advancements in approximate Machine Unlearning for Diffusion Models.