# Separable Multi-Concept Erasure from Diffusion Models

arXiv: https://arxiv.org/abs/2402.05947 · HTML: https://mlsanity.com/paper/2402.05947/

## Key facts

- Cited by 28 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 48 of its 52 references that are in the map.
- First posted on arXiv 3 Feb 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, 30 of 48)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [Swapping Autoencoder for Deep Image Manipulation](https://mlsanity.com/paper/2007.00653/) (2020)
- [To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now](https://mlsanity.com/paper/2310.11868/) (2023)
- [Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models](https://mlsanity.com/paper/2302.04222/) (2023)
- [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://mlsanity.com/paper/2211.08332/) (2022)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [fastai: A Layered API for Deep Learning](https://mlsanity.com/paper/2002.04688/) (2020)

## Built on by (most cited first, 28 of 28)

- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning](https://mlsanity.com/paper/2405.19237/) (2024)
- [UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models](https://mlsanity.com/paper/2402.11846/) (2024)
- [SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models](https://mlsanity.com/paper/2503.07392/) (2025)
- [Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning](https://mlsanity.com/paper/2405.07288/) (2024)
- [Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization](https://mlsanity.com/paper/2504.09039/) (2025)
- [Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models](https://mlsanity.com/paper/2412.15341/) (2024)
- [Mass Concept Erasure in Diffusion Models with Concept Hierarchy](https://mlsanity.com/paper/2601.03305/) (2026)
- [Yuan: Yielding Unblemished Aesthetics Through A Unified Network for Visual Imperfections Removal in Generated Images](https://mlsanity.com/paper/2501.08505/) (2025)
- [Replication in Visual Diffusion Models: A Survey and Outlook](https://mlsanity.com/paper/2408.00001/) (2024)
- [Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression](https://mlsanity.com/paper/2505.19398/) (2025)
- [Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning](https://mlsanity.com/paper/2601.03190/) (2026)
- [Unlearning Concepts from Text-to-Video Diffusion Models](https://mlsanity.com/paper/2407.14209/) (2024)
- [BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning](https://mlsanity.com/paper/2601.09172/) (2026)
- [AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors](https://mlsanity.com/paper/2501.00054/) (2024)
- [MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models](https://mlsanity.com/paper/2506.19257/) (2025)
- [DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation](https://mlsanity.com/paper/2509.21433/) (2025)
- [Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking](https://mlsanity.com/paper/2601.06163/) (2026)
- [Closed-Form Concept Erasure via Double Projections](https://mlsanity.com/paper/2604.10032/) (2026)
- [Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models](https://mlsanity.com/paper/2603.06640/) (2026)
- [Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models](https://mlsanity.com/paper/2610.05601/) (2026)
- [DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing](https://mlsanity.com/paper/2410.05694/) (2024)
- [Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information](https://mlsanity.com/paper/2603.00992/) (2026)
- [Relationship-Aware Safety Unlearning for Multimodal LLMs](https://mlsanity.com/paper/2603.14185/) (2026)
- [CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models](https://mlsanity.com/paper/2606.01658/) (2026)
- [SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models](https://mlsanity.com/paper/2606.15819/) (2026)
- [Gaussian Core LoRA: Distribution-Aware Dynamic Adaptation for Broad Concept Erasure](https://mlsanity.com/paper/2609.01433/) (2026)
- [Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning](https://mlsanity.com/paper/2610.14514/) (2026)

## Abstract (arXiv)

Large-scale diffusion models, known for their impressive image generation capabilities, have raised concerns among researchers regarding social impacts, such as the imitation of copyrighted artistic styles. In response, existing approaches turn to machine unlearning techniques to eliminate unsafe concepts from pre-trained models. However, these methods compromise the generative performance and neglect the coupling among multi-concept erasures, as well as the concept restoration problem. To address these issues, we propose a Separable Multi-concept Eraser (SepME), which mainly includes two parts: the generation of concept-irrelevant representations and the weight decoupling. The former aims to avoid unlearning substantial information that is irrelevant to forgotten concepts. The latter separates optimizable model weights, making each weight increment correspond to a specific concept erasure without affecting generative performance on other concepts. Specifically, the weight increment for erasing a specified concept is formulated as a linear combination of solutions calculated based on other known undesirable concepts. Extensive experiments indicate the efficacy of our approach in eliminating concepts, preserving model performance, and offering flexibility in the erasure or recovery of various concepts.