# Erased or Dormant? Rethinking Concept Erasure Through Reversibility arXiv: https://arxiv.org/abs/2505.16174 ยท HTML: https://mlsanity.com/paper/2505.16174/ ## Key facts - Cited by 9 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 47 of its 60 references that are in the map. - First posted on arXiv 22 May 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 47) - [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) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [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) - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022) - [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022) - [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023) - [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021) - [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) - [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021) - [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023) - [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023) - [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022) - [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022) - [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023) - [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022) - [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023) - [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023) - [InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning](https://mlsanity.com/paper/2304.03411/) (2023) - [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (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) - [A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2001.06937/) (2020) - [Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2405.15234/) (2024) - [Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models](https://mlsanity.com/paper/2407.12383/) (2024) ## Built on by (most cited first, 9 of 9) - [Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models](https://mlsanity.com/paper/2510.03302/) (2025) - [Machine Unlearning under Retain-Forget Entanglement](https://mlsanity.com/paper/2603.26569/) (2026) - [Closed-Form Concept Erasure via Double Projections](https://mlsanity.com/paper/2604.10032/) (2026) - [PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models](https://mlsanity.com/paper/2603.21547/) (2026) - [Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models](https://mlsanity.com/paper/2605.25941/) (2026) - [Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework](https://mlsanity.com/paper/2605.18150/) (2026) - [Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure](https://mlsanity.com/paper/2609.33445/) (2026) - [Data Unlearning via Inverse Distillation](https://mlsanity.com/paper/2609.36099/) (2026) - [Motion Concept Unlearning in Video Diffusion Models](https://mlsanity.com/paper/2609.36832/) (2026) ## Abstract (arXiv) To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a complementary and fundamental question: do current concept erasure techniques genuinely remove the ability to generate targeted concepts, or do they merely achieve superficial, prompt-specific suppression? We systematically evaluate the robustness and reversibility of two representative concept erasure methods, Unified Concept Editing and Erased Stable Diffusion, by probing their ability to eliminate targeted generative behaviors in text-to-image models. These methods attempt to suppress undesired semantic concepts by modifying internal model parameters, either through targeted attention edits or model-level fine-tuning strategies. To rigorously assess whether these techniques truly erase generative capacity, we propose an instance-level evaluation strategy that employs lightweight fine-tuning to explicitly test the reactivation potential of erased concepts. Through quantitative metrics and qualitative analyses, we show that erased concepts often reemerge with substantial visual fidelity after minimal adaptation, indicating that current methods suppress latent generative representations without fully eliminating them. Our findings reveal critical limitations in existing concept erasure approaches and highlight the need for deeper, representation-level interventions and more rigorous evaluation standards to ensure genuine, irreversible removal of concepts from generative models.