SnapSafe: Enabling Selective Image Privacy Through YOLO and AES-Protected Facial Encryption with QR Code
Andri Santoso, Samsul Huda, Tuy Tan Nguyen, Yuta Kodera, Yasuyuki Nogami · 2024
In the digital age, organizations commonly use photos to share their activities for brand visibility. However, it is crucial to safeguard the facial information of individuals depicted in these photos to prevent potential misuse. In this paper, we propose a single-party security system for enabling selective image privacy with a focus on facial regions, called SnapSafe. It adopts the YOLOv8 deep learning model for face detection, AES encryption for security, and QR technology to store the encrypted face region coordinates. Our evaluation assesses the effectiveness of the system through the usability of its face locking and unlocking processes, alongside an analysis of its running time. The results demonstrate the system's proficiency in executing face protection tasks with high accuracy and minimal time overhead, thus indicating its suitability for real-time applications.