Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedges
This addresses security concerns for hypergraph-based machine learning systems, representing an incremental advance in adversarial attack methods.
The paper tackles the vulnerability of Hypergraph Neural Networks (HGNNs) to adversarial attacks by proposing IE-Attack, a framework that injects homogeneous nodes into elite hyperedges, improving attack performance and imperceptibility compared to state-of-the-art methods.
Recent studies have shown that Hypergraph Neural Networks (HGNNs) are vulnerable to adversarial attacks. Existing approaches focus on hypergraph modification attacks guided by gradients, overlooking node spanning in the hypergraph and the group identity of hyperedges, thereby resulting in limited attack performance and detectable attacks. In this manuscript, we present a novel framework, i.e., Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedges (IE-Attack), to tackle these challenges. Initially, utilizing the node spanning in the hypergraph, we propose the elite hyperedges sampler to identify hyperedges to be injected. Subsequently, a node generator utilizing Kernel Density Estimation (KDE) is proposed to generate the homogeneous node with the group identity of hyperedges. Finally, by injecting the homogeneous node into elite hyperedges, IE-Attack improves the attack performance and enhances the imperceptibility of attacks. Extensive experiments are conducted on five authentic datasets to validate the effectiveness of IE-Attack and the corresponding superiority to state-of-the-art methods.