# Toward Robust and Accurate Adversarial Camouflage Generation against Vehicle Detectors Source: [Toward Robust and Accurate Adversarial Camouflage Generation against Vehicle Detectors]() Collection index: [llms.txt]() Data updated: 2025-12-19T05:00:04.526Z Authors: Jiawei Zhou, Linye Lyu, Daojing He, Yu Li Published: 2024-11-15T08:17:08.000Z ## Abstract Adversarial camouflage is a widely used physical attack against vehicle detectors for its superiority in multi-view attack performance. One promising approach involves using differentiable neural renderers to facilitate adversarial camouflage optimization through gradient back-propagation. However, existing methods often struggle to capture environmental characteristics during the rendering process or produce adversarial textures that can precisely map to the target vehicle. Moreover, these approaches neglect diverse weather conditions, reducing the efficacy of generated camouflage across varying weather scenarios. To tackle these challenges, we propose a robust and accurate camouflage generation method, namely RAUCA. The core of RAUCA is a novel neural rendering component, End-to-End Neural Renderer Plus (E2E-NRP), which can accurately optimize and project vehicle textures and render images with environmental characteristics such as lighting and weather. In addition, we integrate a multi-weather dataset for camouflage generation, leveraging the E2E-NRP to enhance the attack robustness. Experimental results on six popular object detectors show that RAUCA-final outperforms existing methods in both simulation and real-world settings. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on Physical Domain Strong Light](): Object Detection; Physical Domain Strong Light; AP@0.5: 36.11. - [Object Detection on Physical Domain Low Light](): Object Detection; Physical Domain Low Light; AP@0.5: 45.34. - [Object Detection on Physical Domain Average](): Object Detection; Physical Domain Average; AP@0.5: 34.52. - [Object Detection on Physical Domain Normal Light](): Object Detection; Physical Domain Normal Light; AP@0.5: 22.12. - [Object Detection on Vehicle Detection (test)](): Object Detection; Vehicle detection (test); AP@0.5: 40.41. - [Object Detection on CARLA simulator (test)](): Object Detection; CARLA simulator (test); AP@0.5: 76.74. ## Original sources and implementation [Original paper]() [PDF]()