Dual-Targeted adversarial example in evasion attack on graph neural networks

Dual-Targeted adversarial example in evasion attack on graph neural networks

Abstract This study proposes a novel approach for generating dual-targeted adversarial examples in Graph Neural Networks (GNNs), significantly advancing the field of graph-based adversarial attacks. Unlike traditional methods that focus on inducing specific misclassifications in a single model, our...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyun Kwon, Dae-Jin Kim
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Subjects:
Graph neural network
Adversarial example
Evasion attack
Node classification
Machine learning
Online Access:https://doi.org/10.1038/s41598-025-85493-2
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://doi.org/10.1038/s41598-025-85493-2

Similar Items