Search:
Match:
2 results
Research Paper#Graph Neural Networks, Security, Backdoor Attacks🔬 ResearchAnalyzed: Jan 3, 2026 06:28

HeteroHBA: Backdoor Attack on Heterogeneous Graphs

Published:Dec 31, 2025 06:38
1 min read
ArXiv

Analysis

This paper addresses the vulnerability of Heterogeneous Graph Neural Networks (HGNNs) to backdoor attacks. It proposes a novel generative framework, HeteroHBA, to inject backdoors into HGNNs, focusing on stealthiness and effectiveness. The research is significant because it highlights the practical risks of backdoor attacks in heterogeneous graph learning, a domain with increasing real-world applications. The proposed method's performance against existing defenses underscores the need for stronger security measures in this area.
Reference

“HeteroHBA consistently achieves higher attack success than prior backdoor baselines with comparable or smaller impact on clean accuracy.”

PermalinkArXiv
Research Paper#Hypergraph Neural Networks, Robustness Prediction, Deep Learning🔬 ResearchAnalyzed: Jan 3, 2026 20:17

Hypergraph Isomorphism Network for Robustness Prediction

Published:Dec 26, 2025 12:25
1 min read
ArXiv

Analysis

This paper addresses the limitations of existing deep learning methods in assessing the robustness of complex systems, particularly those modeled as hypergraphs. It proposes a novel Hypergraph Isomorphism Network (HWL-HIN) that leverages the expressive power of the Hypergraph Weisfeiler-Lehman test. This is significant because it offers a more accurate and efficient way to predict robustness compared to traditional methods and existing HGNNs, which is crucial for engineering and economic applications.
Reference

“The proposed method not only outperforms existing graph-based models but also significantly surpasses conventional HGNNs in tasks that prioritize topological structure representation.”

PermalinkArXiv