TY  - CONF
ID  - SisLab4260
UR  - https://doi.org/10.1145/3394171.3414047
A1  - Vu, Xuan Son
A1  - Le, Duc Trong
A1  - Edlund, Christoffer
A1  - Jiang, Lili
A1  - Nguyen, Hoang D.
Y1  - 2020/10//
N2  - With the rapid growth of Internet media, content tagging has become an important topic with many multimedia understanding applications, including efficient organisation and search. Nevertheless, existing visual tagging approaches are susceptible to inherent privacy risks in which private information may be exposed unintentionally. The use of anonymisation and privacy-protection methods is desirable, but with the expense of task performance.Therefore, this paper proposes an end-to-end framework (SGTN) using Graph Transformer and Convolutional Networks to significantly improve classification and privacy preservation of visual data. Especially, we employ several mechanisms such as differential privacy based graph construction and noise-induced graph transformation to protect the privacy of knowledge graphs. Our approach unveils new state-of-the-art on MS-COCO dataset in various semisupervised settings. In addition, we showcase a real experiment in the education domain to address the automation of sensitive document tagging. Experimental results show that our approach achieves an excellent balance of model accuracy and privacy preservation on both public and private datasets. Codes are available at https://github.com/ReML-AI/sgtn.
TI  - Privacy-Preserving Visual Content Tagging using Graph Transformer Networks
AV  - public
T2  - The 28th ACM International Conference on Multimedia
ER  -