HGNN Shield: Defending Hypergraph Neural Networks Against High-Order Structure Attack
Summary
Hypergraph Neural Networks (HGNNs, which are AI models that learn from data where connections can link multiple items together instead of just pairs) can be weakened by structural attacks that corrupt their connections and reduce accuracy. HGNN Shield is a defense framework with two main components: Hyperedge-Dependent Estimation (which assesses how important each connection is within the network) and High-Order Shield (which detects and removes harmful connections before the AI processes data). Experiments show the framework improves performance by an average of 9.33% compared to existing defenses.
Solution / Mitigation
The HGNN Shield defense framework addresses the vulnerability through two modules: (1) Hyperedge-Dependent Estimation (HDE) that 'prioritizes vertex dependencies within hyperedges and adapts traditional connectivity measures to hypergraphs, facilitating precise structural modifications,' and (2) High-Order Shield (HOS) positioned before convolutional layers, which 'consists of three submodules: Hyperpath Cut, Hyperpath Link, and Hyperpath Refine' that 'collectively detect, disconnect, and refine adversarial connections, ensuring robust message propagation.'
Classification
Related Issues
Original source: http://ieeexplore.ieee.org/document/11316283
First tracked: March 9, 2026 at 08:01 PM
Classified by LLM (prompt v3) · confidence: 85%