Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
Not provided in the abstract
Abstract
This paper investigates the impact of stealthy false data injection on city pedestrian counting systems and proposes a method to enhance the integrity of these systems using physics-constrained digital twins.
Reality Card
The proposed method achieves a significant reduction in worst-case corruption of estimated pedestrian flow fields, with an attack margin of 0.54 against a single compromised device.
The attack margin reaches 0.54 against a single compromised device and falls to 0.19 when a third of the fleet is compromised.
The method's effectiveness is highly dependent on the conservation law and the specific structure of the street graph, which may limit generalizability.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.