# Ungeneralizable Examples

arXiv: https://arxiv.org/abs/2404.14016 · HTML: https://mlsanity.com/paper/2404.14016/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [Fast Yet Effective Machine Unlearning](https://mlsanity.com/paper/2111.08947/) (2021)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Dataset Distillation: A Comprehensive Review](https://mlsanity.com/paper/2301.07014/) (2023)
- [Adversarial Examples Make Strong Poisons](https://mlsanity.com/paper/2106.10807/) (2021)
- [Adversarial Frontier Stitching for Remote Neural Network Watermarking](https://mlsanity.com/paper/1711.01894/) (2017)
- [Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks](https://mlsanity.com/paper/2006.12557/) (2020)
- [Dataset Distillation via Factorization](https://mlsanity.com/paper/2210.16774/) (2022)
- [DAWN: Dynamic Adversarial Watermarking of Neural Networks](https://mlsanity.com/paper/1906.00830/) (2019)
- [A Survey On Universal Adversarial Attack](https://mlsanity.com/paper/2103.01498/) (2021)
- [Defending Against Model Stealing Attacks with Adaptive Misinformation](https://mlsanity.com/paper/1911.07100/) (2019)
- [Defending against Model Stealing via Verifying Embedded External Features](https://mlsanity.com/paper/2112.03476/) (2021)
- [Transferable Unlearnable Examples](https://mlsanity.com/paper/2210.10114/) (2022)
- [Undistillable: Making A Nasty Teacher That CANNOT teach students](https://mlsanity.com/paper/2105.07381/) (2021)
- [CUDA: Convolution-based Unlearnable Datasets](https://mlsanity.com/paper/2303.04278/) (2023)
- [Mutual-modality Adversarial Attack with Semantic Perturbation](https://mlsanity.com/paper/2312.12768/) (2023)
- [Safe Distillation Box](https://mlsanity.com/paper/2112.03695/) (2021)
- [Partial Network Cloning](https://mlsanity.com/paper/2303.10597/) (2023)

## Built on by (most cited first, 9 of 9)

- [Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need](https://mlsanity.com/paper/2410.03644/) (2024)
- [Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization](https://mlsanity.com/paper/2510.10982/) (2025)
- [StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization](https://mlsanity.com/paper/2406.00275/) (2024)
- [A Survey on Unlearnable Data](https://mlsanity.com/paper/2503.23536/) (2025)
- [Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle](https://mlsanity.com/paper/2608.04314/) (2026)
- [CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning](https://mlsanity.com/paper/2505.19119/) (2025)
- [Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective](https://mlsanity.com/paper/2410.00878/) (2024)
- [Learning to Generate Cross-Task Unexploitable Examples](https://mlsanity.com/paper/2512.13416/) (2025)
- [Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training](https://mlsanity.com/paper/2604.24350/) (2026)

## Abstract (arXiv)

The training of contemporary deep learning models heavily relies on publicly available data, posing a risk of unauthorized access to online data and raising concerns about data privacy. Current approaches to creating unlearnable data involve incorporating small, specially designed noises, but these methods strictly limit data usability, overlooking its potential usage in authorized scenarios. In this paper, we extend the concept of unlearnable data to conditional data learnability and introduce UnGeneralizable Examples (UGEs). UGEs exhibit learnability for authorized users while maintaining unlearnability for potential hackers. The protector defines the authorized network and optimizes UGEs to match the gradients of the original data and its ungeneralizable version, ensuring learnability. To prevent unauthorized learning, UGEs are trained by maximizing a designated distance loss in a common feature space. Additionally, to further safeguard the authorized side from potential attacks, we introduce additional undistillation optimization. Experimental results on multiple datasets and various networks demonstrate that the proposed UGEs framework preserves data usability while reducing training performance on hacker networks, even under different types of attacks.