<ul><li>TACO is a novel framework that generates adversarial camouflage patterns on 3D vehicle models to deceive object detectors.</li><li>It integrates differentiable rendering with a Photorealistic Rendering Network to optimize adversarial textures targeted at YOLOv8.</li><li>Experimental evaluations demonstrate that TACO significantly degrades YOLOv8's detection performance and exhibits transferability to other object detection models.</li><li>TACO achieves an AP@0.5 of 0.0099 on unseen test data.</li></ul>

TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors

Discover more