Targeted Discrepancy Attacks: Crafting Selective Adversarial Examples in Graph Neural Networks

Targeted Discrepancy Attacks: Crafting Selective Adversarial Examples in Graph Neural Networks

In this study, we present a novel approach to adversarial attacks for graph neural networks (GNNs), specifically addressing the unique challenges posed by graphical data. Unlike traditional adversarial attacks, which aim to perturb the input data to induce misclassifications in the target model, our...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyun Kwon, Jang-Woon Baek
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Graph neural network
adversarial example
evasion attack
node classification
machine learning
Online Access:https://ieeexplore.ieee.org/document/10829739/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10829739/

Similar Items