Protecting by attacking: A personal information protecting method with cross-modal adversarial examples

doi:10.1016/j.neucom.2023.126481

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Protecting by attacking: A personal information protecting method with cross-modal adversarial examples
	Zhao, Mengnan 2; Wang, Bo 1; Guo, Weikuo 1; Wang, Wei 3
刊名	NEUROCOMPUTING
	2023-09-28
卷号	551 页码:11
关键词	Security Cross-modal Image captioning Adversarial attacks
ISSN号	0925-2312
DOI	10.1016/j.neucom.2023.126481
通讯作者	Wang, Bo(bowang@dlut.edu)
英文摘要	Recent years' development of AI technology brings more convenience to our life while at the same time increasing the risk of personal information leakage. In this work, we try to protect personal information contained in the images by generating adversarial examples to fool the image captioning models. The generated adversarial examples are user-oriented which means the users can manipulate or hide sensitive information on the text output as they wish. By doing so, our personal information can be well protected from image captioning models. To fulfill the task, we adopt five kinds of adversarial attack. Experimental results show our method can successfully protect user security. The Pytorch & REG; implementations can be downloaded from an open-source GitHub project (https://github.com/Dlut-lab-zmn/ImageCaptioning-Attack/). & COPY; 2023 Elsevier B.V. All rights reserved.
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:001033827500001
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53789]
专题	多模态人工智能系统全国重点实验室
通讯作者	Wang, Bo
作者单位	1.Dalian Univ Technol, Sch Informat & Commun Engn, Dalian 116081, Peoples R China 2.Dalian Univ Technol, Sch Comp Sci & Technol, Dalian 116081, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100089, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Mengnan,Wang, Bo,Guo, Weikuo,et al. Protecting by attacking: A personal information protecting method with cross-modal adversarial examples[J]. NEUROCOMPUTING,2023,551:11.
APA	Zhao, Mengnan,Wang, Bo,Guo, Weikuo,&Wang, Wei.(2023).Protecting by attacking: A personal information protecting method with cross-modal adversarial examples.NEUROCOMPUTING,551,11.
MLA	Zhao, Mengnan,et al."Protecting by attacking: A personal information protecting method with cross-modal adversarial examples".NEUROCOMPUTING 551(2023):11.