Graph-Based Multimodal Traffic Prediction Under Adversarial Diffusion Across Varying Network Scales Versus Standard GCNs

Real-time traffic prediction models play a pivotal role in smart mobility systems and have been widely used in route guidance, emerging mobility services, and advanced traffic management systems. With the availability of massive traffic data, neural network-based deep learning methods, especially the graph convolutional networks (GCN) have demonstrated outstanding performance in mining spatio-temporal information and achieving high prediction accuracy. Recent studies reveal the vulnerability of GCN under adversarial attacks, while there is a lack of studies to understand the vulnerability issu

Research goal: How scalable are graph-based multimodal traffic prediction models under adversarial diffusion attacks when evaluated on datasets with varying graph sizes (e.g., small vs. large-scale traffic networks), and how does this compare to standard GCN-based models?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.