Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon-Reference-Cited by-同舟云学术

Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Zhong Yiqi¹,Liu Xianming¹,Zhai Deming¹,Jiang Junjun¹,Ji Xiangyang²

Affiliation:

1. Harbin Institute of Technology

2. Tsinghua University

Funder

National Natural Science Foundation of China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9878378/9878366/09878995.pdf?arnumber=9878995

Reference34 articles.

1. Shadow Remover: Image Shadow Removal Based on Illumination Recovering Optimization

2. Learning black-box attackers with transferable priors and query feedback;yang;Advances in neural information processing systems,2020

3. Improving Transferability of Adversarial Examples With Input Diversity

4. Boosting the transferability of adversarial samples via attention;weibin;Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,0

5. Improving Shadow Suppression for Illumination Robust Face Recognition

Cited by 61 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Shadow-aware decomposed transformer network for shadow detection and removal;Pattern Recognition;2024-12

2. Adversarial Infrared Curves: An attack on infrared pedestrian detectors in the physical world;Neural Networks;2024-10

3. State-of-the-art optical-based physical adversarial attacks for deep learning computer vision systems;Expert Systems with Applications;2024-09

4. Adversarial sample attacks algorithm based on cycle-consistent generative networks;Applied Soft Computing;2024-09

5. OptiCloak: Blinding Vision-Based Autonomous Driving Systems Through Adversarial Optical Projection;IEEE Internet of Things Journal;2024-09-01