A Computer Vision Approach to Prevent Screen Photographing and Ensure LGPD Compliance

Traditional Data Loss Prevention (DLP) tools cannot prevent a smartphone from photographing sensitive information displayed on a monitor. This paper proposes a computer vision-based system that detects smartphones positioned toward a screen and triggers immediate screen obfuscation. Using a standard webcam and a YOLOv8n pipeline implemented in Python on Google Colab, the final model achieved a precision of 100%, recall of 98.3%, mAP50 of 99.5%, and a total pipeline latency of 8.01 ± 0.57 ms, demonstrating strong feasibility as a low-cost LGPD compliance tool.