# Mass Concept Erasure in Diffusion Models with Concept Hierarchy

arXiv: https://arxiv.org/abs/2601.03305 · HTML: https://mlsanity.com/paper/2601.03305/

## Key facts

- Cited by 14 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 34 of its 48 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## 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 34)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [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)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024)
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications](https://mlsanity.com/paper/2312.16145/) (2023)
- [SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation](https://mlsanity.com/paper/2410.12761/) (2024)
- [Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers](https://mlsanity.com/paper/2311.17717/) (2023)
- [Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts](https://mlsanity.com/paper/2504.12782/) (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)
- [Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters](https://mlsanity.com/paper/2412.06143/) (2024)
- [BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models](https://mlsanity.com/paper/2410.07273/) (2024)
- [Separable Multi-Concept Erasure from Diffusion Models](https://mlsanity.com/paper/2402.05947/) (2024)
- [Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization](https://mlsanity.com/paper/2504.09039/) (2025)
- [Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate](https://mlsanity.com/paper/2506.22806/) (2025)
- [DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving](https://mlsanity.com/paper/2407.15661/) (2024)
- [GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework](https://mlsanity.com/paper/2312.16429/) (2023)
- [LW2G: Learning Whether to Grow for Prompt-based Continual Learning](https://mlsanity.com/paper/2409.18860/) (2024)

## Built on by (most cited first, 14 of 14)

- [LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts](https://mlsanity.com/paper/2602.11564/) (2026)
- [TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention](https://mlsanity.com/paper/2601.21900/) (2026)
- [Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion](https://mlsanity.com/paper/2602.01183/) (2026)
- [Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking](https://mlsanity.com/paper/2601.06163/) (2026)
- [Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers](https://mlsanity.com/paper/2603.25074/) (2026)
- [UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning](https://mlsanity.com/paper/2602.03410/) (2026)
- [Orthogonal Concept Erasure for Diffusion Models](https://mlsanity.com/paper/2605.28902/) (2026)
- [The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable Optimization](https://mlsanity.com/paper/2602.00175/) (2026)
- [Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models](https://mlsanity.com/paper/2605.25941/) (2026)
- [Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation](https://mlsanity.com/paper/2602.05339/) (2026)
- [BARRIER: Bounded Activation Regions for Robust Information Erasure](https://mlsanity.com/paper/2605.15737/) (2026)
- [SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs](https://mlsanity.com/paper/2606.09868/) (2026)
- [AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate](https://mlsanity.com/paper/2607.08337/) (2026)
- [Motion Concept Unlearning in Video Diffusion Models](https://mlsanity.com/paper/2609.36832/) (2026)

## Abstract (arXiv)

The success of diffusion models has raised concerns about the generation of unsafe or harmful content, prompting concept erasure approaches that fine-tune modules to suppress specific concepts while preserving general generative capabilities. However, as the number of erased concepts grows, these methods often become inefficient and ineffective, since each concept requires a separate set of fine-tuned parameters and may degrade the overall generation quality. In this work, we propose a supertype-subtype concept hierarchy that organizes erased concepts into a parent-child structure. Each erased concept is treated as a child node, and semantically related concepts (e.g., macaw, and bald eagle) are grouped under a shared parent node, referred to as a supertype concept (e.g., bird). Rather than erasing concepts individually, we introduce an effective and efficient group-wise suppression method, where semantically similar concepts are grouped and erased jointly by sharing a single set of learnable parameters. During the erasure phase, standard diffusion regularization is applied to preserve denoising process in unmasked regions. To mitigate the degradation of supertype generation caused by excessive erasure of semantically related subtypes, we propose a novel method called Supertype-Preserving Low-Rank Adaptation (SuPLoRA), which encodes the supertype concept information in the frozen down-projection matrix and updates only the up-projection matrix during erasure. Theoretical analysis demonstrates the effectiveness of SuPLoRA in mitigating generation performance degradation. We construct a more challenging benchmark that requires simultaneous erasure of concepts across diverse domains, including celebrities, objects, and pornographic content.