Revisiting the Adversarial Robustness of Graph-Based Traffic Forecasting

본문 미리보기

arXiv:2607.27604v1 Announce Type: new Abstract: Traffic forecasting by graph-based AI is a critical component of intelligent transportation systems, motivating security research on robustness to malicious sensor readings. We argue that prior robustness evaluations are largely shaped by unrealistic threat models and untargeted objectives, so both attacks and defenses must be revisited. We study a practical adversary with limited model knowledge and the ability to monitor and manipulate only a fe