Effectively Learning Moir´e QR Code Decryption from Simulated Data

Moir´e QR Code is a secure encrypted QR code system that can protect the user’s QR code displayed on the screen from being accessed by attackers. However, conventional decryption methods based on image processing techniques suffer from intensive computation and significant decryption latency in practical mobile applications. In this work, we propose a deep learning-based Moir´e QR code decryption framework and achieve an excellent decryption performance. Considering the sensitivity of the Moir´e phenomenon, collecting training data in the real world is extremely labor and material intensive. To overcome this issue, we develop a physical screen-imaging Moir´e simulation methodology to generate a synthetic dataset that covers the entire Moir´e-visible area. Extensive experiments show that the proposed decryption network can achieve a low decryption latency (0.02 seconds) and a high decryption rate (98.8%), compared with the previous decryption method with decryption latency (5.4 seconds) and decryption rate (98.6%).

In International Conference on Computer Communications