MSAI: Masking Sensitive Area of Image on IoT Cameras

Jinqiang Liu,
Yining Liu,
Lei Cui,
Shui Yu,


In smart cities, images captured by Internet of Things (IoT) cameras are transmitted to data center via intermediate nodes. The shared images can reveal much of sensitive information of users, which has caused increasing privacy concerns. Various encryption-based techniques have been developed for privacy preserving. However, they are not suitable for IoT cameras due to the high computation cost. In this paper, we propose a lightweight image privacy protection scheme considering personalized protection requirements of users. We first introduce an object detection algorithm to detect and pick up sensitive areas in images according to the specific requirements of users. Then, we propose a membrane-based method to mask the sensitive areas before uploading images to the data center. In particular, the masking operation does not require much computing resources on the used cloud platform, and the masking size of membrane can be dynamically adjusted. Our experiments on real-world datasets demonstrate the effectiveness and feasibility of the proposed scheme.

Citation Format:
Jinqiang Liu, Yining Liu, Lei Cui, Shui Yu, "MSAI: Masking Sensitive Area of Image on IoT Cameras," Journal of Internet Technology, vol. 22, no. 7 , pp. 1553-1561, Dec. 2021.

Full Text:



  • There are currently no refbacks.

Published by Executive Committee, Taiwan Academic Network, Ministry of Education, Taipei, Taiwan, R.O.C
JIT Editorial Office, Office of Library and Information Services, National Dong Hwa University
No. 1, Sec. 2, Da Hsueh Rd., Shoufeng, Hualien 974301, Taiwan, R.O.C.
Tel: +886-3-931-7314  E-mail: