What is it about?

Steganography and digital watermarking are the tasks of hiding recoverable data in image pixels. Deep neural network (DNN) based image steganography and watermarking techniques are quickly replacing traditional hand-engineered pipelines. DNN based watermarking techniques have drastically improved the message capacity, imperceptibility and robustness of the embedded watermarks. However, this improvement comes at the cost of increased computational overhead of the watermark encoder neural network. In this work, we design the first accelerator platform FastStamp to perform DNN based steganography and digital watermarking of images on hardware.

Featured Image

Why is it important?

Steganography and digital watermarking are the tasks of hiding recoverable data in image pixels. Such technology has several applications, such as transmitting secret messages, copyright protection, establishing media ownership, and embedding invisible QR codes into images. Deep neural network (DNN) based image steganography and watermarking techniques are quickly replacing traditional hand-engineered pipelines. DNN based watermarking techniques have drastically improved the message capacity, imperceptibility and robustness of the embedded watermarks. However, this improvement comes at the cost of increased computational overhead of the watermark encoder neural network. The best performing neural image watermarking encoders are parameterized by around half a million floating point parameters, which makes it challenging to deploy such systems on resource constrained hardware such as FPGAs or handheld devices. Our work aims to embed watermarks in images and videos in real-time as they are being captured. Embedding the watermarks at the hardware level can not only reduce the latency of the watermarking process but also enable media authentication and provenance by leveraging unique hardware signatures from PUFs or secure enclaves as the watermarking data.

Read the Original

This page is a summary of: FastStamp, October 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3508352.3549357.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page