# Unlearnable Graph: Protecting Graphs from Unauthorized Exploitation

arXiv: https://arxiv.org/abs/2303.02568 · HTML: https://mlsanity.com/paper/2303.02568/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 3 references that are in the map.
- First posted on arXiv 5 Mar 2023.

## Builds on (most cited first, 3 of 3)

- [A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT](https://mlsanity.com/paper/2302.09419/) (2023)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release](https://mlsanity.com/paper/2103.02683/) (2021)

## Built on by (most cited first, 5 of 5)

- [Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise](https://mlsanity.com/paper/2311.13091/) (2023)
- [Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Masking](https://mlsanity.com/paper/2403.10573/) (2024)
- [A Survey on Unlearnable Data](https://mlsanity.com/paper/2503.23536/) (2025)
- [To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model](https://mlsanity.com/paper/2605.14291/) (2026)
- [MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks](https://mlsanity.com/paper/2609.00696/) (2026)

## Abstract (arXiv)

While the use of graph-structured data in various fields is becoming increasingly popular, it also raises concerns about the potential unauthorized exploitation of personal data for training commercial graph neural network (GNN) models, which can compromise privacy. To address this issue, we propose a novel method for generating unlearnable graph examples. By injecting delusive but imperceptible noise into graphs using our Error-Minimizing Structural Poisoning (EMinS) module, we are able to make the graphs unexploitable. Notably, by modifying only 5% at most of the potential edges in the graph data, our method successfully decreases the accuracy from 77.33% to 42.47% on the COLLAB dataset.