Based Physical Attack

Based physical attacks exploit the vulnerability of deep neural networks (DNNs) to carefully crafted physical perturbations, aiming to deceive object detectors and other vision systems in real-world scenarios. Current research focuses on developing increasingly stealthy and robust attacks using various methods, including manipulating infrared radiation, reflected light, and projected light patterns (e.g., lasers, projectors, neon beams), often employing optimization algorithms like particle swarm optimization or genetic algorithms to generate effective adversarial perturbations. These attacks highlight significant security risks for numerous vision-based applications, such as autonomous driving and security systems, demanding the development of robust countermeasures and more resilient DNN architectures.

Papers

December 21, 2023

Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World
Chengyin Hu, Weiwen Shi
Physical World Adversarial Defense Thermal Infrared Adversarial Infrared Based Physical Attack Infrared Attack Infrared Domain

December 11, 2023

Adversarial Camera Patch: An Effective and Robust Physical-World Attack on Object Detectors
Kalibinuer Tiliwalidi
Object Detector Adversarial Patch Image Patch Physical World Attack Based Physical Attack

July 14, 2023

RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World
Donghua Wang, Wen Yao, Tingsong Jiang, Chao Li, Xiaoqian Chen
Adversarial Attack Physical World Adversarial Pattern Optical Adversarial Based Physical Attack

September 19, 2022

September 2, 2022

Adversarial Color Film: Effective Physical-World Attack to DNNs
Chengyin Hu, Weiwen Shi
Deep Neural Network Adversarial Training Physical World Attack Based Physical Attack Adversarial Color

June 2, 2022

Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs
Chengyin Hu, Yilong Wang, Kalibinuer Tiliwalidi, Wen Li
Deep Neural Network Physical World Attack Based Physical Attack

April 2, 2022

Adversarial Neon Beam: A Light-based Physical Attack to DNNs
Chengyin Hu, Weiwen Shi, Wen Li
Deep Neural Network Based Physical Attack