StegaStamp: Invisible Hyperlinks in Physical Photographs

By Matthew Tancik, Ben Mildenhall, Ren Ng. Computer Vision and Pattern Recognition, 2019

591 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e7fabcd45e8077bdff75a8764186c92ee3f2670a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Siwei Lyu
2. Luc Van Gool
3. Baoyuan Wu
4. Yuezun Li
5. Ran He
6. Mario Fritz
7. Weiming Zhang
8. Ming-Hsuan Yang

Citations in the corpus

• Data Feedback Loops: Model-driven Amplification of Dataset Biases (2022, methodology): “For hyperparameter tuning, we trained the ResNet18 CRF for [20 , 30 , 45 , 60] epochs on dataset sizes of [20 k , 50 k , 75 k , 100 k ] .”
• Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data (2020, methodology): “Recent works replace hand-crafted hiding procedures with neural network encoding [4, 18, 45, 58, 55, 42, 33].”
• MBRS: Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression (2021, methodology): “Our baseline for comparison are [27], [17] and [22].”
• Distortion Agnostic Deep Watermarking (2020, background): “Modeling more complex and realistic image distortions also broadened the scope in terms of application [40, 35].”
• HiNet: Deep Image Hiding by Invertible Network (2021, background): “[27] proposed a StegaStamp framework to hide hyperlinks in a physical photograph and successfully retrieve it after decoding.”
• Invisible Backdoor Attack with Sample-Specific Triggers (2020, methodology): “Specifically, inspired by DNN-based image steganography [2, 51, 39], we generate sample-specific invisible additive noises as backdoor triggers by encoding an attacker-specified string into benign images through an encoder-decoder network.”
• Robust Invisible Video Watermarking with Attention (2019, methodology): “We are motivated by the recent success of deep learning and adversarial training methods in data hiding tasks as shown by [32, 28].”