# Concept Unlearning by Modeling Key Steps of Diffusion Process

arXiv: https://arxiv.org/abs/2507.06526 · HTML: https://mlsanity.com/paper/2507.06526/

## Key facts

- Cited by 5 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 43 of its 60 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## 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 43)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (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)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?](https://mlsanity.com/paper/2310.10012/) (2023)
- [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)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts](https://mlsanity.com/paper/2309.06135/) (2023)
- [Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2405.15234/) (2024)
- [Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models](https://mlsanity.com/paper/2311.12092/) (2023)
- [Diffusion Probabilistic Model Made Slim](https://mlsanity.com/paper/2211.17106/) (2022)
- [A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data](https://mlsanity.com/paper/2402.16991/) (2024)

## Built on by (most cited first, 5 of 5)

- [Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks](https://mlsanity.com/paper/2607.07907/) (2026)
- [Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration](https://mlsanity.com/paper/2604.15829/) (2026)
- [RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2610.01969/) (2026)
- [When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models](https://mlsanity.com/paper/2604.15967/) (2026)
- [Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models](https://mlsanity.com/paper/2610.10859/) (2026)

## Abstract (arXiv)

Text-to-image diffusion models remain susceptible to generating undesirable or harmful content. Although concept unlearning mitigates this risk, existing methods struggle with a critical optimization dilemma: thorough semantic erasure frequently induces the catastrophic forgetting of unrelated generative capabilities. To overcome this challenge, we propose Key Step Concept Unlearning (KSCU). Serving as an integrated methodological refinement deeply motivated by information theory, KSCU explores the profound impact of step scheduling order and reveals that traditional randomized timestep sampling severely disrupts trajectory dependency. We demonstrate that indiscriminately targeting the entire diffusion process is inefficient, as the optimal step range for unlearning inherently varies across different concepts. Rather than globally fine-tuning all timesteps, KSCU explicitly integrates a sequential-scheduling-based Key Step Table, CFG-aware leakage compensation, and prompt augmentation to dynamically isolate optimization to a concept-specific active region. This localized strategy successfully eradicates the target concept while preventing the structural collapse caused by early-step over-optimization. Consequently, KSCU significantly reduces computational overhead and establishes a state-of-the-art trade-off between concept erasure and utility retention. Comprehensive evaluations demonstrate that KSCU consistently delivers superior performance across diverse unlearning tasks, including nudity, style, object classes, and mass instance concepts. For example, in nudity removal, KSCU yields a 96.5% unlearning accuracy alongside a state-of-the-art FID of 14.1.