Flexible Physical Camouflage Generation Based on a Differential Approach

TL;DR

This paper presents FPA, a novel neural rendering method for realistic adversarial camouflage that adapts to lighting and environment, demonstrating high success and transferability in physical and empirical tests.

Contribution

Introduces a differential approach for neural rendering of adversarial camouflage that faithfully simulates lighting and material variations, with a generative diffusion model and physical validation.

Findings

High attack success rate in physical tests

Effective transferability across environments

Versatile camouflage styles with concealment constraints

Abstract

This study introduces a novel approach to neural rendering, specifically tailored for adversarial camouflage, within an extensive 3D rendering framework. Our method, named FPA, goes beyond traditional techniques by faithfully simulating lighting conditions and material variations, ensuring a nuanced and realistic representation of textures on a 3D target. To achieve this, we employ a generative approach that learns adversarial patterns from a diffusion model. This involves incorporating a specially designed adversarial loss and covert constraint loss to guarantee the adversarial and covert nature of the camouflage in the physical world. Furthermore, we showcase the effectiveness of the proposed camouflage in sticker mode, demonstrating its ability to cover the target without compromising adversarial information. Through empirical and physical experiments, FPA exhibits strong performance in terms of attack success rate and transferability. Additionally, the designed sticker-mode camouflage, coupled with a concealment constraint, adapts to the environment, yielding diverse styles of texture. Our findings highlight the versatility and efficacy of the FPA approach in adversarial camouflage applications.