StegaStamp: Invisible Hyperlinks in Physical Photographs
arXiv:1904.05343
Abstract
Printed and digitally displayed photos have the ability to hide imperceptible digital data that can be accessed through internet-connected imaging systems. Another way to think about this is physical photographs that have unique QR codes invisibly embedded within them. This paper presents an architecture, algorithms, and a prototype implementation addressing this vision. Our key technical contribution is StegaStamp, a learned steganographic algorithm to enable robust encoding and decoding of arbitrary hyperlink bitstrings into photos in a manner that approaches perceptual invisibility. StegaStamp comprises a deep neural network that learns an encoding/decoding algorithm robust to image perturbations approximating the space of distortions resulting from real printing and photography. We demonstrates real-time decoding of hyperlinks in photos from in-the-wild videos that contain variation in lighting, shadows, perspective, occlusion and viewing distance. Our prototype system robustly retrieves 56 bit hyperlinks after error correction - sufficient to embed a unique code within every photo on the internet.
CVPR 2020, Project page: http://www.matthewtancik.com/stegastamp
References in corpus (6)
- Robust Physical-World Attacks on Deep Learning Models
- Generating Steganographic Images via Adversarial Training
- DARTS: Deceiving Autonomous Cars with Toxic Signs
- StegNet: Mega Image Steganography Capacity with Deep Convolutional Network
- SteganoGAN: High Capacity Image Steganography with GANs
- Deep ChArUco: Dark ChArUco Marker Pose Estimation
Cited by in corpus (6)
- Robust Invisible Video Watermarking with Attention
- DVMark: A Deep Multiscale Framework for Video Watermarking
- Distortion Agnostic Deep Watermarking
- Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings
- Model Watermarking for Image Processing Networks
- Robust Invisible Hyperlinks in Physical Photographs Based on 3D Rendering Attacks