Although there are a great number of adversarial attacks on deep learning based classifiers, how to attack object detection systems has been rarely studied. In this paper, we propose a Half-Neighbor Masked Projected Gradient Descent (HNM-PGD) based attack, which can generate strong perturbation to fool different kinds of detectors under strict constraints. We also applied the proposed HNM-PGD attack in the CIKM 2020 AnalytiCup Competition, which was ranked within the top 1% on the leaderboard. We release the code at https://github.com/YanghaoZYH/HNM-PGD.
@article{arxiv.2101.00989,
title = {Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks},
author = {Yanghao Zhang and Fu Wang and Wenjie Ruan},
journal= {arXiv preprint arXiv:2101.00989},
year = {2021}
}
Comments
To appear in the Proceedings of the CIKM 2020 Workshops published by CEUR-WS