QwQ2000/WSDM26-Graph-Unlearning-Inversion
WSDM'26 full paper -- "Unlearning Inversion Attack for Graph Neural Networks"
This project helps machine learning researchers and data scientists evaluate the security and privacy risks of Graph Neural Networks (GNNs). It takes a GNN model and a dataset, then demonstrates how an 'inversion attack' could reconstruct sensitive input data. It also shows how 'unlearning' mechanisms can mitigate these privacy breaches.
Use this if you are a researcher or practitioner working with Graph Neural Networks and need to understand or demonstrate their vulnerability to data reconstruction attacks and the effectiveness of unlearning methods.
Not ideal if you are looking for a general-purpose graph analysis tool or a library for building GNNs, as this focuses specifically on privacy and unlearning research.
Stars
8
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/QwQ2000/WSDM26-Graph-Unlearning-Inversion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
QData/TextAttack
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model...
ebagdasa/backdoors101
Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct...
THUYimingLi/backdoor-learning-resources
A list of backdoor learning resources
zhangzp9970/MIA
Unofficial pytorch implementation of paper: Model Inversion Attacks that Exploit Confidence...
LukasStruppek/Plug-and-Play-Attacks
[ICML 2022 / ICLR 2024] Source code for our papers "Plug & Play Attacks: Towards Robust and...