# T2UE: Generating Unlearnable Examples from Text Descriptions

arXiv: https://arxiv.org/abs/2508.03091 · HTML: https://mlsanity.com/paper/2508.03091/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 54 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Builds on (most cited first, 30 of 42)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Large image datasets: A pyrrhic win for computer vision?](https://mlsanity.com/paper/2006.16923/) (2020)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Adversarial Examples Make Strong Poisons](https://mlsanity.com/paper/2106.10807/) (2021)
- [The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI](https://mlsanity.com/paper/2310.16787/) (2023)
- [Availability Attacks Create Shortcuts](https://mlsanity.com/paper/2111.00898/) (2021)
- [Text to Image Generation with Semantic-Spatial Aware GAN](https://mlsanity.com/paper/2104.00567/) (2021)
- [Autoregressive Perturbations for Data Poisoning](https://mlsanity.com/paper/2206.03693/) (2022)
- [Transferable Unlearnable Examples](https://mlsanity.com/paper/2210.10114/) (2022)
- [Data Poisoning Attacks Against Multimodal Encoders](https://mlsanity.com/paper/2209.15266/) (2022)
- [Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples](https://mlsanity.com/paper/2301.01217/) (2022)

## Built on by (most cited first, 3 of 3)

- [Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle](https://mlsanity.com/paper/2608.04314/) (2026)
- [Learning to Generate Cross-Task Unexploitable Examples](https://mlsanity.com/paper/2512.13416/) (2025)
- [SoK: Unlearnability and Unlearning for Model Dememorization](https://mlsanity.com/paper/2605.11592/) (2026)

## Abstract (arXiv)

Large-scale pre-training frameworks like CLIP have revolutionized multimodal learning, but their reliance on web-scraped datasets, frequently containing private user data, raises serious concerns about misuse. Unlearnable Examples (UEs) have emerged as a promising countermeasure against unauthorized model training, employing carefully crafted unlearnable noise to disrupt the learning of meaningful representations from protected data. Current approaches typically generate UEs by jointly optimizing unlearnable noise for both images and their associated text descriptions (or labels). However, this optimization process is often computationally prohibitive for on-device execution, forcing reliance on external third-party services. This creates a fundamental privacy paradox: users must initially expose their data to these very services to achieve protection, thereby compromising privacy in the process. Such a contradiction has severely hindered the development of practical, scalable data protection solutions. To resolve this paradox, we introduce Text-to-Unlearnable Example (T2UE), a novel framework that enables users to generate UEs using only text descriptions. T2UE circumvents the need for original image data by employing a text-to-image (T2I) model to map text descriptions into the image (noise) space, combined with an error-minimization framework to produce effective unlearnable noise. Extensive experiments show that T2UE-protected data substantially degrades performance in downstream tasks (e.g., cross-modal retrieval) for state-of-the-art models. Notably, the protective effect generalizes across diverse architectures and even to supervised learning settings. Our work demonstrates the feasibility of "zero-contact data protection", where personal data can be safeguarded based solely on their textual descriptions, eliminating the need for direct data exposure.