# Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts

arXiv: https://arxiv.org/abs/2403.12326 · HTML: https://mlsanity.com/paper/2403.12326/

## Key facts

- Cited by 8 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 24 of its 32 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [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)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (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)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [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)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters](https://mlsanity.com/paper/2002.01808/) (2020)
- [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)
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022)
- [What the DAAM: Interpreting Stable Diffusion Using Cross Attention](https://mlsanity.com/paper/2210.04885/) (2022)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models](https://mlsanity.com/paper/2305.13873/) (2023)
- [Editing Implicit Assumptions in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.08084/) (2023)
- [Anti-DreamBooth: Protecting users from personalized text-to-image synthesis](https://mlsanity.com/paper/2303.15433/) (2023)

## Built on by (most cited first, 8 of 8)

- [Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation](https://mlsanity.com/paper/2410.15618/) (2024)
- [Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them](https://mlsanity.com/paper/2501.18950/) (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)
- [Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks](https://mlsanity.com/paper/2607.07907/) (2026)
- [Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols](https://mlsanity.com/paper/2507.19894/) (2025)
- [From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation](https://mlsanity.com/paper/2512.13953/) (2025)
- [Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment](https://mlsanity.com/paper/2506.22685/) (2025)

## Abstract (arXiv)

Diffusion models have demonstrated remarkable capability in generating high-quality visual content from textual descriptions. However, since these models are trained on large-scale internet data, they inevitably learn undesirable concepts, such as sensitive content, copyrighted material, and harmful or unethical elements. While previous works focus on permanently removing such concepts, this approach is often impractical, as it can degrade model performance and lead to irreversible loss of information. In this work, we introduce a novel concept-hiding approach that makes unwanted concepts inaccessible to public users while allowing controlled recovery when needed. Instead of erasing knowledge from the model entirely, we incorporate a learnable prompt into the cross-attention module, acting as a secure memory that suppresses the generation of hidden concepts unless a secret key is provided. This enables flexible access control -- ensuring that undesirable content cannot be easily generated while preserving the option to reinstate it under restricted conditions. Our method introduces a new paradigm where concept suppression and controlled recovery coexist, which was not feasible in prior works. We validate its effectiveness on the Stable Diffusion model, demonstrating that hiding concepts mitigate the risks of permanent removal while maintaining the model's overall capability.