A graph backdoor detection method for data collection scenarios

A graph backdoor detection method for data collection scenarios

Abstract Data collection is an effective way to build a better Graph Neural Network (GNN) model, but it also makes it easy for attackers to implant backdoors into the model through data poisoning. In this work, we propose a backdoor detection method of graph for data collection scenarios (CGBD). Dif...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaogang Xing, Ming Xu, Yujing Bai, Dongdong Yang
Format: Article
Language:English
Published: SpringerOpen 2025-01-01
Series:Cybersecurity
Subjects:
Machine learning
Graph neural networks
Network security
Data collection
Backdoor detection
Online Access:https://doi.org/10.1186/s42400-024-00305-w
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items