Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Blackknife: Hard-Label Query-Limited Black-Box Attacks on Heterogeneous Graph Neural Networks
Honglin Gao, Junhao Ren, Lan Zhao +3
Heterogeneous graph neural networks (HGNNs) have achieved strong performance in modeling complex graph-structured data with multiple node and relation types. However, their robustn…
cs.LG2025
HeteroHBA: A Generative Structure-Manipulating Backdoor Attack on Heterogeneous Graphs
Honglin Gao, Lan Zhao, Junhao Ren +2
Heterogeneous graph neural networks (HGNNs) have achieved strong performance in many real-world applications, yet targeted backdoor poisoning on heterogeneous graphs remains less s…
cs.LG2025
HeteroBA: A Structure-Manipulating Backdoor Attack on Heterogeneous Graphs
Honglin Gao, Xiang Li, Lan Zhao +1
Heterogeneous graph neural networks (HGNNs) have recently drawn increasing attention for modeling complex multi-relational data in domains such as recommendation, finance, and soci…