# ACE: Attentional Concept Erasure in Diffusion Models

arXiv: https://arxiv.org/abs/2504.11850 · HTML: https://mlsanity.com/paper/2504.11850/

## Key facts

- Cited by 3 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 37 of its 39 references that are in the map.
- First posted on arXiv 16 Apr 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 30 of 37)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [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)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models](https://mlsanity.com/paper/2305.10120/) (2023)
- [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)
- [Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers](https://mlsanity.com/paper/2311.17717/) (2023)
- [EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers](https://mlsanity.com/paper/2412.20413/) (2024)
- [SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders](https://mlsanity.com/paper/2501.18052/) (2025)
- [R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model](https://mlsanity.com/paper/2405.16341/) (2024)
- [Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation](https://mlsanity.com/paper/2410.15618/) (2024)
- [Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models](https://mlsanity.com/paper/2307.05977/) (2023)
- [All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2312.12807/) (2023)
- [TraSCE: Trajectory Steering for Concept Erasure](https://mlsanity.com/paper/2412.07658/) (2024)
- [Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models](https://mlsanity.com/paper/2503.19783/) (2025)
- [Implicit Concept Removal of Diffusion Models](https://mlsanity.com/paper/2310.05873/) (2023)
- [Pruning for Robust Concept Erasing in Diffusion Models](https://mlsanity.com/paper/2405.16534/) (2024)
- [MUNBa: Machine Unlearning via Nash Bargaining](https://mlsanity.com/paper/2411.15537/) (2024)
- [ACE: Anti-Editing Concept Erasure in Text-to-Image Models](https://mlsanity.com/paper/2501.01633/) (2025)
- [Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models](https://mlsanity.com/paper/2408.01014/) (2024)
- [Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion](https://mlsanity.com/paper/2503.13769/) (2025)
- [Unveiling Concept Attribution in Diffusion Models](https://mlsanity.com/paper/2412.02542/) (2024)
- [DuMo: Dual Encoder Modulation Network for Precise Concept Erasure](https://mlsanity.com/paper/2501.01125/) (2025)

## Built on by (most cited first, 3 of 3)

- [Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models](https://mlsanity.com/paper/2510.03302/) (2025)
- [Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression](https://mlsanity.com/paper/2505.19398/) (2025)
- [GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2511.12968/) (2025)

## Abstract (arXiv)

Large text-to-image diffusion models have demonstrated remarkable image synthesis capabilities, but their indiscriminate training on Internet-scale data has led to learned concepts that enable harmful, copyrighted, or otherwise undesirable content generation. We address the task of concept erasure in diffusion models, i.e., removing a specified concept from a pre-trained model such that prompting the concept (or related synonyms) no longer yields its depiction, while preserving the model's ability to generate other content. We propose a novel method, Attentional Concept Erasure (ACE), that integrates a closed-form attention manipulation with lightweight fine-tuning. Theoretically, we formulate concept erasure as aligning the model's conditional distribution on the target concept with a neutral distribution. Our approach identifies and nullifies concept-specific latent directions in the cross-attention modules via a gated low-rank adaptation, followed by adversarially augmented fine-tuning to ensure thorough erasure of the concept and its synonyms. Empirically, we demonstrate on multiple benchmarks, including object classes, celebrity faces, explicit content, and artistic styles, that ACE achieves state-of-the-art concept removal efficacy and robustness. Compared to prior methods, ACE better balances generality (erasing concept and related terms) and specificity (preserving unrelated content), scales to dozens of concepts, and is efficient, requiring only a few seconds of adaptation per concept. We will release our code to facilitate safer deployment of diffusion models.