Understanding Visual Privacy Protection: A Generalized Framework With an Instance on Facial Privacy

被引:3
作者
Zhang, Yushu [1 ]
Ji, Junhao [1 ]
Wen, Wenying [2 ]
Zhu, Youwen [1 ]
Xia, Zhihua [3 ]
Weng, Jian [3 ]
机构
[1] Nanjing Univ Aeronaut & Astronaut, Coll Comp Sci & Technol, Nanjing 211106, Peoples R China
[2] Jiangxi Univ Finance & Econ, Coll Informat Technol, Nanchang 330013, Peoples R China
[3] Jinan Univ, Coll Cyber Secur, Guangzhou 510632, Peoples R China
关键词
Privacy; Protection; Visualization; Face recognition; Perturbation methods; Usability; Faces; Visual privacy; generalized framework; identity protection; attribute control; diffusion model;
D O I
10.1109/TIFS.2024.3389572
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
With the widespread application of computer vision, the scenarios in terms of visual privacy have become increasingly diverse and meanwhile numerous studies have been conducted to address privacy concerns in these scenarios. However, these studies are individually tailored for specific scenarios, making their layouts challenging to be drawn upon easily. When encountering a new scenario, it takes significant additional efforts to redesign a scheme due to the low referability of previous works. To tackle this issue, we explore commonalities among existing works and propose a generalized framework to meet the demand for visual privacy protection in various scenarios. Our framework is elaborately organized into several crucial steps, including privacy definition, scenario abstraction, algorithm design, and effect evaluation. It serves as a guide for researchers to efficiently design visual privacy protection schemes. In our framework, we establish a unified standard for quantifying privacy and introduce a novel constrained optimization theory to balance privacy and usability, which contributes to a broader understanding of visual privacy protection. Furthermore, we present an instance under the guidance of the framework that can support identity protection and attribute control scenarios through a diffusion-based model. Extensive experimental results demonstrate the effectiveness of our framework.
引用
收藏
页码:5046 / 5059
页数:14
相关论文
共 38 条
[1]   I Know That Person: Generative Full Body and Face De-Identification of People in Images [J].
Brkic, Karla ;
Sikiric, Ivan ;
Hrkac, Tomislav ;
Kalafatic, Zoran .
2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, :1319-1328
[2]  
Chatzikyriakidis E, 2019, IEEE IMAGE PROC, P684, DOI [10.1109/icip.2019.8803803, 10.1109/ICIP.2019.8803803]
[3]   FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems [J].
Chen, Lu ;
Sun, Jiao ;
Xu, Wei .
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2020, PT III, 2021, 12459 :547-563
[4]  
Dhariwal P, 2021, ADV NEUR IN, V34
[5]   AdvDrop: Adversarial Attack to DNNs by Dropping Information [J].
Duan, Ranjie ;
Chen, Yuefeng ;
Niu, Dantong ;
Yang, Yun ;
Qin, A. K. ;
He, Yuan .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :7486-7495
[6]   Large-scale Privacy Protection in Google Street View [J].
Frome, Andrea ;
Cheung, German ;
Abdulkader, Ahmad ;
Zennaro, Marco ;
Wu, Bo ;
Bissacco, Alessandro ;
Adam, Hartwig ;
Neven, Hartmut ;
Vincent, Luc .
2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, :2373-2380
[7]   Fast R-CNN [J].
Girshick, Ross .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1440-1448
[8]  
He KM, 2020, IEEE T PATTERN ANAL, V42, P386, DOI [10.1109/TPAMI.2018.2844175, 10.1109/ICCV.2017.322]
[9]   AttGAN: Facial Attribute Editing by Only Changing What You Want [J].
He, Zhenliang ;
Zuo, Wangmeng ;
Kan, Meina ;
Shan, Shiguang ;
Chen, Xilin .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (11) :5464-5478
[10]   Collaborative Diffusion for Multi-Modal Face Generation and Editing [J].
Huang, Ziqi ;
Chan, Kelvin C. K. ;
Jiang, Yuming ;
Liu, Ziwei .
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, :6080-6090