# Backdooring Textual Inversion for Concept Censorship

arXiv: https://arxiv.org/abs/2308.10718 · HTML: https://mlsanity.com/paper/2308.10718/

## 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 30 of its 43 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

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

- [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)
- [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)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [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)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [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)
- [Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors](https://mlsanity.com/paper/2203.13131/) (2022)
- [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](https://mlsanity.com/paper/2204.14217/) (2022)
- [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](https://mlsanity.com/paper/2204.08583/) (2022)
- [Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models](https://mlsanity.com/paper/2302.04222/) (2023)
- [word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method](https://mlsanity.com/paper/1402.3722/) (2014)
- [How to Backdoor Diffusion Models?](https://mlsanity.com/paper/2212.05400/) (2022)
- [Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning](https://mlsanity.com/paper/2305.04175/) (2023)
- [TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets](https://mlsanity.com/paper/2303.05762/) (2023)
- [Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.10701/) (2023)

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

- [R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model](https://mlsanity.com/paper/2405.16341/) (2024)
- [Threats, Attacks, and Defenses in Machine Unlearning: A Survey](https://mlsanity.com/paper/2403.13682/) (2024)
- [A Survey on Personalized Content Synthesis with Diffusion Models](https://mlsanity.com/paper/2405.05538/) (2024)
- [T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models](https://mlsanity.com/paper/2407.04215/) (2024)
- [Espresso: Robust Concept Filtering in Text-to-Image Models](https://mlsanity.com/paper/2404.19227/) (2024)
- [Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation](https://mlsanity.com/paper/2503.06453/) (2025)
- [Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models](https://mlsanity.com/paper/2503.17724/) (2025)
- [Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2504.20518/) (2025)
- [Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack](https://mlsanity.com/paper/2510.00635/) (2025)
- [Detecting Malicious Concepts without Image Generation in AI-Generated Content (AIGC)](https://mlsanity.com/paper/2502.08921/) (2025)
- [EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation](https://mlsanity.com/paper/2406.15863/) (2024)
- [Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models](https://mlsanity.com/paper/2508.01605/) (2025)
- [IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis](https://mlsanity.com/paper/2603.15679/) (2026)
- [Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure](https://mlsanity.com/paper/2609.33445/) (2026)

## Abstract (arXiv)

Recent years have witnessed success in AIGC (AI Generated Content). People can make use of a pre-trained diffusion model to generate images of high quality or freely modify existing pictures with only prompts in nature language. More excitingly, the emerging personalization techniques make it feasible to create specific-desired images with only a few images as references. However, this induces severe threats if such advanced techniques are misused by malicious users, such as spreading fake news or defaming individual reputations. Thus, it is necessary to regulate personalization models (i.e., concept censorship) for their development and advancement. In this paper, we focus on the personalization technique dubbed Textual Inversion (TI), which is becoming prevailing for its lightweight nature and excellent performance. TI crafts the word embedding that contains detailed information about a specific object. Users can easily download the word embedding from public websites like Civitai and add it to their own stable diffusion model without fine-tuning for personalization. To achieve the concept censorship of a TI model, we propose leveraging the backdoor technique for good by injecting backdoors into the Textual Inversion embeddings. Briefly, we select some sensitive words as triggers during the training of TI, which will be censored for normal use. In the subsequent generation stage, if the triggers are combined with personalized embeddings as final prompts, the model will output a pre-defined target image rather than images including the desired malicious concept. To demonstrate the effectiveness of our approach, we conduct extensive experiments on Stable Diffusion, a prevailing open-sourced text-to-image model. Our code, data, and results are available at https://concept-censorship.github.io.