HeteroHBA: A Generative Structure-Manipulating Backdoor Attack on Heterogeneous Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Honglin, Zhao, Lan, Ren, Junhao, Li, Xiang, Xiao, Gaoxi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915701127643136
author Gao, Honglin
Zhao, Lan
Ren, Junhao
Li, Xiang
Xiao, Gaoxi
author_facet Gao, Honglin
Zhao, Lan
Ren, Junhao
Li, Xiang
Xiao, Gaoxi
contents Heterogeneous graph neural networks (HGNNs) have achieved strong performance in many real-world applications, yet targeted backdoor poisoning on heterogeneous graphs remains less studied. We consider backdoor attacks for heterogeneous node classification, where an adversary injects a small set of trigger nodes and connections during training to force specific victim nodes to be misclassified into an attacker-chosen label at test time while preserving clean performance. We propose HeteroHBA, a generative backdoor framework that selects influential auxiliary neighbors for trigger attachment via saliency-based screening and synthesizes diverse trigger features and connection patterns to better match the local heterogeneous context. To improve stealthiness, we combine Adaptive Instance Normalization (AdaIN) with a Maximum Mean Discrepancy (MMD) loss to align the trigger feature distribution with benign statistics, thereby reducing detectability, and we optimize the attack with a bilevel objective that jointly promotes attack success and maintains clean accuracy. Experiments on multiple real-world heterogeneous graphs with representative HGNN architectures show that HeteroHBA consistently achieves higher attack success than prior backdoor baselines with comparable or smaller impact on clean accuracy; moreover, the attack remains effective under our heterogeneity-aware structural defense, CSD. These results highlight practical backdoor risks in heterogeneous graph learning and motivate the development of stronger defenses.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24665
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HeteroHBA: A Generative Structure-Manipulating Backdoor Attack on Heterogeneous Graphs
Gao, Honglin
Zhao, Lan
Ren, Junhao
Li, Xiang
Xiao, Gaoxi
Machine Learning
Heterogeneous graph neural networks (HGNNs) have achieved strong performance in many real-world applications, yet targeted backdoor poisoning on heterogeneous graphs remains less studied. We consider backdoor attacks for heterogeneous node classification, where an adversary injects a small set of trigger nodes and connections during training to force specific victim nodes to be misclassified into an attacker-chosen label at test time while preserving clean performance. We propose HeteroHBA, a generative backdoor framework that selects influential auxiliary neighbors for trigger attachment via saliency-based screening and synthesizes diverse trigger features and connection patterns to better match the local heterogeneous context. To improve stealthiness, we combine Adaptive Instance Normalization (AdaIN) with a Maximum Mean Discrepancy (MMD) loss to align the trigger feature distribution with benign statistics, thereby reducing detectability, and we optimize the attack with a bilevel objective that jointly promotes attack success and maintains clean accuracy. Experiments on multiple real-world heterogeneous graphs with representative HGNN architectures show that HeteroHBA consistently achieves higher attack success than prior backdoor baselines with comparable or smaller impact on clean accuracy; moreover, the attack remains effective under our heterogeneity-aware structural defense, CSD. These results highlight practical backdoor risks in heterogeneous graph learning and motivate the development of stronger defenses.
title HeteroHBA: A Generative Structure-Manipulating Backdoor Attack on Heterogeneous Graphs
topic Machine Learning
url https://arxiv.org/abs/2512.24665