Graph-Native Attention Acceleration for Attack Detection in Cyber-Physical Systems

What the math gives to ML

The paper offers a concrete hybrid attention mechanism for graph-structured systems: restrict one attention branch to physically or communicationally valid neighbors, add a global linear-mixing branch, and combine them with a node-wise learnable gate. Its transferable asset is a computational decomposition that preserves local relational selectivity while avoiding the quadratic cost of dense global attention. The direct neural-network transfer is a drop-in GraphGHHA layer for graph transformers, spatiotemporal forecasting, molecular networks, and multi-agent models, with the adjacency mask supplied by the task graph. The key falsifiable prediction is that attention cost scales with the number of edges plus a linear global term, rather than with the square of the node count.