From 2D-Patch to 3D-Camouflage: A Review of Physical Adversarial Attack in Object Detection
Open Access
- 29 October 2025
- journal article
- review article
- Published by MDPI AG in Electronics
- Vol. 14 (21) , 4236
Abstract
Deep neural networks have demonstrated remarkable performance in object detection tasks; however, they remain highly susceptible to adversarial attacks. Previous surveys in computer vision have provided considerable coverage of physical adversarial attacks, yet the aspect of systematically categorizing and evaluating their physical deployment methods for object detection has not received commensurate focus. To address this gap, we categorize physical adversarial attacks into three primary classes based on the physical deployment of adversarial patterns: manipulating 2D physical objects, injecting adversarial signals, and placing 3D adversarial camouflage. These categories are further analyzed and compared across nine key attributes. Furthermore, we elucidate the relationship between physical adversarial attacks against object detection models and two critical properties: transferability and perceptibility. Our findings indicate that while attacks involving the manipulation of 2D physical objects are relatively straightforward to deploy, their adversarial patterns are often perceptible to human observers. Similarly, 3D adversarial camouflage tends to lack stealthiness, whereas adversarial signal injection offers stronger imperceptibility. However, all three attack types exhibit limited transferability across different models and modalities. Finally, we discuss current challenges and propose actionable directions for future research, aiming to foster the development of more robust object detection systems.Keywords
Funding Information
- Open Foundation of Key Laboratory of Cyberspace Security, Ministry of Education of China (KLCS20240211)
This publication has 132 references indexed in Scilit:
- Adversarial Infrared Curves: An attack on infrared pedestrian detectors in the physical worldNeural Networks, 2024
- Adversarial infrared blocks: A multi-view black-box attack to thermal infrared detectors in physical worldNeural Networks, 2024
- A review of convolutional neural networks in computer visionArtificial Intelligence Review, 2024
- A survey of the vision transformers and their CNN-transformer based variantsArtificial Intelligence Review, 2023
- Differential evolution based dual adversarial camouflage: Fooling human eyes and object detectorsNeural Networks, 2023
- Robust convolutional neural networks against adversarial attacks on medical imagesPattern Recognition, 2022
- PatchAttack: A Black-Box Texture-Based Attack with Reinforcement Learning2020
- Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors2020
- Adversarial T-Shirt! Evading Person Detectors in a Physical World2020
- ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector2019