Knowledge Commons of Institute of Automation,CAS
Adversarial attacks on Faster R-CNN object detector | |
Wang, Yutong1,2![]() ![]() ![]() | |
发表期刊 | NEUROCOMPUTING
![]() |
ISSN | 0925-2312 |
2020-03-21 | |
卷号 | 382期号:无页码:87-95 |
摘要 | Adversarial attacks have stimulated research interests in the field of deep learning security. However, most of existing adversarial attack methods are developed on classification. In this paper, we use Projected Gradient Descent (PGD), the strongest first-order attack method on classification, to produce adversarial examples on the total loss of Faster R-CNN object detector. Compared with the state-of-the-art Dense Adversary Generation (DAG) method, our attack is more efficient and more powerful in both white-box and black-box attack settings, and is applicable in a variety of neural network architectures. On Pascal VOC2007, under white-box attack, DAG has 5.92% mAP on Faster R-CNN with VGG16 backbone using 41.42 iterations on average, while our method achieves 0.90% using only 4 iterations. We also analyze the difference of attacks between classification and detection, and find that in addition to misclassification, adversarial examples on detection also lead to mis-localization. Besides, we validate the adversarial effectiveness of both Region Proposal Network (RPN) and Fast R-CNN loss, the components of the total loss. Our research will provide inspiration for further efforts in adversarial attacks on other vision tasks. (C) 2019 Elsevier B.V. All rights reserved. |
关键词 | Adversarial attack Object detection White-box attack Black-box attack |
DOI | 10.1016/j.neucom.2019.11.051 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key R&D Program of China[2018YFC1704400] ; National Natural Science Foundation of China[U1811463] ; National Natural Science Foundation of China[U1811463] ; National Key R&D Program of China[2018YFC1704400] |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000512881200010 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/28589 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
通讯作者 | Wang, Kunfeng |
作者单位 | 1.The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.College of Information Science and Technology, Beijing University of Chemical Technology 4.School of Mathematical Sciences, Peking University |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang, Yutong,Wang, Kunfeng,Zhu, Zhanxing,et al. Adversarial attacks on Faster R-CNN object detector[J]. NEUROCOMPUTING,2020,382(无):87-95. |
APA | Wang, Yutong,Wang, Kunfeng,Zhu, Zhanxing,&Wang, Fei-Yue.(2020).Adversarial attacks on Faster R-CNN object detector.NEUROCOMPUTING,382(无),87-95. |
MLA | Wang, Yutong,et al."Adversarial attacks on Faster R-CNN object detector".NEUROCOMPUTING 382.无(2020):87-95. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
1-s2.0-S092523121931(5655KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论