Deep Learning for Privacy in Multimedia

被引:3
作者
Cavallaro, Andrea [1 ]
Malekzadeh, Mohammad [1 ]
Shamsabadi, Ali Shahin [1 ]
机构
[1] Queen Mary Univ London, Ctr Intelligent Sensing, London, England
来源
MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA | 2020年
基金
英国工程与自然科学研究理事会;
关键词
Privacy; Multimedia; Personal Information; Adversarial Examples; Data Transformations;
D O I
10.1145/3394171.3418551
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We discuss the design and evaluation of machine learning algorithms that provide users with more control on the multimedia information they share. We introduce privacy threats for multimedia data and key features of privacy protection. We cover privacy threats and mitigating actions for images, videos, and motion-sensor data from mobile and wearable devices, and their protection from unwanted, automatic inferences. The tutorial offers theoretical explanations followed by examples with software developed by the presenters and distributed as open source.
引用
收藏
页码:4777 / 4778
页数:2
相关论文
共 18 条
[1]   Privacy as a Feature for Body-Worn Cameras [J].
Cross, Maria S. ;
Cavallaro, Andrea .
IEEE SIGNAL PROCESSING MAGAZINE, 2020, 37 (04) :148-+
[2]  
Li C. Y., 2019, P IEEE INT C AC SPEE
[3]  
Malekzadeh M., 2018, P IEEE ACM INT C INT
[4]  
Malekzadeh M., 2018, P 1 ACM WORKSH PRIV
[5]  
Malekzadeh M., 2020, P C MACH LEARN SYST
[6]  
Malekzadeh M., 2019, P IEEE ACM INT C INT
[7]   Privacy and utility preserving sensor-data transformations [J].
Malekzadeh, Mohammad ;
Clegg, Richard G. ;
Cavallaro, Andrea ;
Haddadi, Hamed .
PERVASIVE AND MOBILE COMPUTING, 2020, 63
[8]  
Osia S. A., 2018, IEEE COMP SPEC ISS M
[9]  
Osia Seyed Ali, 2020, IEEE Internet of Things Journal
[10]  
Osia Seyed Ali, 2018, IEEE T KNOWLEDGE DAT