Poster: Exploring Disruption by Intelligent Reflective Surfaces in mmWave Radar Object Classification

Intelligent Reflective Surfaces (IRS) are an emerging research focus aimed at enhancing non-line-of-sight wireless communications by manipulating radio reflections. However, when embedded within objects, IRS may disrupt mmWave radar object classification by altering reflected features. In this study, we explore the adverse effects of a misconfigured IRS on radar classification. We prototyped an IRS with configurations that can either induce destructive interference with the object's reflected signals or deflect these reflections away from the radar using beamforming techniques. Experiments using a 24 GHz radar to detect four everyday objects revealed a significant drop in classification accuracy due to this interference. These findings underscore a significant vulnerability in the increasingly pervasive deployment of mmWave radar for object classification, highlighting the urgent need for robust countermeasures.