Physical Adversarial

Physical adversarial attacks exploit vulnerabilities in AI systems, particularly computer vision models, by introducing carefully crafted physical perturbations to real-world objects, causing misclassification or evasion. Current research focuses on benchmarking attack effectiveness across various object detection models (e.g., YOLO, Faster R-CNN) and developing robust attack methods, including those utilizing 3D modeling and dynamic optical perturbations, to overcome challenges like varying viewpoints and lighting conditions. This research is crucial for enhancing the safety and security of AI-powered systems, especially in critical applications like autonomous driving, where misidentification of objects can have severe consequences.

Papers

September 15, 2024

Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective
Ningfei Wang, Shaoyuan Xie, Takami Sato, Yunpeng Luo, Kaidi Xu, Qi Alfred Chen
Adversarial Attack Traffic Sign Recognition System Approach Physical Adversarial

August 17, 2024

PADetBench: Towards Benchmarking Physical Attacks against Object Detection
Jiawei Lian, Jianhong Pan, Lefan Wang, Yi Wang, Lap-Pui Chau, Shaohui Mei
Adversarial Image Physical Adversarial Benchmark Attack Physical Attack

May 16, 2024

Infrared Adversarial Car Stickers
Xiaopei Zhu, Yuqiu Liu, Zhanhao Hu, Jianmin Li, Xiaolin Hu
Physical Adversarial Level IR Adversarial Infrared Infrared Attack

March 8, 2024

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao
Adversarial Attack Adversarial Perturbation 3D Point Cloud Imperceptible Pattern Physical Adversarial Adversarial Shape Prior

November 14, 2023

Physical Adversarial Examples for Multi-Camera Systems
Ana Răduţoiu, Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
Adversarial Example Multi Camera Multiple Camera Physical Adversarial Successful Adversarial Attack

November 1, 2023

Adversarial Examples in the Physical World: A Survey
Jiakai Wang, Donghua Wang, Jin Hu, Siyang Wu, Tingsong Jiang, Wen Yao, Aishan Liu, Xianglong Liu
Timely Survey Adversarial Attack Adversarial Example Physical World Physical Adversarial Robust Adversarial Learning

August 23, 2023

Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack
Ningfei Wang, Yunpeng Luo, Takami Sato, Kaidi Xu, Qi Alfred Chen
Adversarial Attack Autonomous Driving Evasion Attack Driving Policy Physical Adversarial Adversarial Evasion Attack System Level

August 7, 2023

Exploring the Physical World Adversarial Robustness of Vehicle Detection
Wei Jiang, Tianyuan Zhang, Shuangcheng Liu, Weiyu Ji, Zichao Zhang, Gang Xiao
Adversarial Attack Vehicle Detection Adversarial Scenario Physical Adversarial Real World Detection

July 24, 2023

Why Don't You Clean Your Glasses? Perception Attacks with Dynamic Optical Perturbations
Yi Han, Matthew Chan, Eric Wengrowski, Zhuohuan Li, Nils Ole Tippenhauer, Mani Srivastava, Saman Zonouz, Luis Garcia
Adversarial Attack Man in the Middle Attack Physical Adversarial Full Frame Eyeglass Model

April 11, 2023

Benchmarking the Physical-world Adversarial Robustness of Vehicle Detection
Tianyuan Zhang, Yisong Xiao, Xiaoya Zhang, Hao Li, Lu Wang
Adversarial Attack Detection Model Vehicle Detection Physical Adversarial Detection Benchmark

September 28, 2022

A Survey on Physical Adversarial Attack in Computer Vision
Donghua Wang, Wen Yao, Tingsong Jiang, Guijian Tang, Xiaoqian Chen
Timely Survey Adversarial Attack Computer Vision Adversarial Example Physical Adversarial

March 23, 2022

Powerful Physical Adversarial Examples Against Practical Face Recognition Systems
Inderjeet Singh, Toshinori Araki, Kazuya Kakizaki
Adversarial Example Face Recognition Physical Adversarial

March 18, 2022

DTA: Physical Camouflage Attacks using Differentiable Transformation Network
Naufal Suryanto, Yongsu Kim, Hyoeun Kang, Harashta Tatimma Larasati, Youngyeo Yun, Thi-Thu-Huong Le, Hunmin Yang, Se-Yoon Oh, Howon Kim
Adversarial Attack Differentiable Neural Physical Adversarial Adversarial CAmouflage Camouflage Generation Differentiable Transformation Attack Camouflage Attack

March 7, 2022

Adversarial Texture for Fooling Person Detectors in the Physical World
Zhanhao Hu, Siyuan Huang, Xiaopei Zhu, Fuchun Sun, Bo Zhang, Xiaolin Hu
Adversarial Example Adversarial Patch Physical World Generative Attack Physical Adversarial Adversarial Texture Person Detector

February 22, 2022

On the Effectiveness of Adversarial Training against Backdoor Attacks
Yinghua Gao, Dongxian Wu, Jingfeng Zhang, Guanhao Gan, Shu-Tao Xia, Gang Niu, Masashi Sugiyama
Adversarial Training Backdoor Attack Physical Adversarial

January 17, 2022

Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems
Wei Jia, Zhaojun Lu, Haichun Zhang, Zhenglin Liu, Jie Wang, Gang Qu
Autonomous Vehicle Adversarial Example DNN Model Adversarial Patch Character Eye Traffic Sign Recognition Physical Adversarial