Transferable Hypergraph Attack via Injecting Nodes into Pivotal Hyperedges

TL;DR

This paper introduces TH-Attack, a novel transferable hypergraph attack method that injects malicious nodes into pivotal hyperedges to improve attack transferability and effectiveness against hypergraph neural networks.

Contribution

The paper proposes a hyperedge recognizer and feature inverter to generate malicious nodes, enhancing attack transferability by targeting pivotal hyperedges in HGNNs.

Findings

TH-Attack outperforms state-of-the-art methods in experiments

Effective across six real-world datasets

Improves attack transferability and success rate

Abstract

Recent studies have demonstrated that hypergraph neural networks (HGNNs) are susceptible to adversarial attacks. However, existing methods rely on the specific information mechanisms of target HGNNs, overlooking the common vulnerability caused by the significant differences in hyperedge pivotality along aggregation paths in most HGNNs, thereby limiting the transferability and effectiveness of attacks. In this paper, we present a novel framework, i.e., Transferable Hypergraph Attack via Injecting Nodes into Pivotal Hyperedges (TH-Attack), to address these limitations. Specifically, we design a hyperedge recognizer via pivotality assessment to obtain pivotal hyperedges within the aggregation paths of HGNNs. Furthermore, we introduce a feature inverter based on pivotal hyperedges, which generates malicious nodes by maximizing the semantic divergence between the generated features and the pivotal hyperedges features. Lastly, by injecting these malicious nodes into the pivotal hyperedges, TH-Attack improves the transferability and effectiveness of attacks. Extensive experiments are conducted on six authentic datasets to validate the effectiveness of TH-Attack and the corresponding superiority to state-of-the-art methods.