ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion

TL;DR

ACTIVE introduces a novel physical camouflage framework that creates universal, robust adversarial textures capable of hiding any 3D vehicle from detectors across different viewpoints, models, and real-world scenarios.

Contribution

The paper presents ACTIVE, a new framework with techniques for universal, transferable, and natural-looking adversarial camouflage for vehicles, surpassing prior methods in robustness and transferability.

Findings

Outperforms existing methods on 15 detector models including YOLOv7.

Demonstrates strong transferability to different vehicle classes and segmentation tasks.

Effective in real-world scenarios, showing practical applicability.

Abstract

Adversarial camouflage has garnered attention for its ability to attack object detectors from any viewpoint by covering the entire object's surface. However, universality and robustness in existing methods often fall short as the transferability aspect is often overlooked, thus restricting their application only to a specific target with limited performance. To address these challenges, we present Adversarial Camouflage for Transferable and Intensive Vehicle Evasion (ACTIVE), a state-of-the-art physical camouflage attack framework designed to generate universal and robust adversarial camouflage capable of concealing any 3D vehicle from detectors. Our framework incorporates innovative techniques to enhance universality and robustness, including a refined texture rendering that enables common texture application to different vehicles without being constrained to a specific texture map, a novel stealth loss that renders the vehicle undetectable, and a smooth and camouflage loss to enhance the naturalness of the adversarial camouflage. Our extensive experiments on 15 different models show that ACTIVE consistently outperforms existing works on various public detectors, including the latest YOLOv7. Notably, our universality evaluations reveal promising transferability to other vehicle classes, tasks (segmentation models), and the real world, not just other vehicles.