Neural Network Watermarking

Neural Network Watermarking (MPAI-NNW) is an MPAI Technical Specification providing the means to measure, for a given size of the watermarking payload, the ability of:

  1. The watermark inserter to inject a payload without deteriorating the NN performance.
  2. The watermark detector to recognise the presence and the watermark decoder to successfully retrieve the payload of the inserted watermark.
  3. The watermark inserter to inject a payload and the watermark detector/decoder to detect/decode a payload from a watermarked model or from any of its inferences at a measured computational cost.

Visit the About MPAI-NNW page for an introduction to the MPAI-NNW standard.

Watch YouTube video Non-WimTV video Presentation:  MPAI-NNW DV3.0

MPAI has developed the MPAI-NNW Technical Specification and Reference Software.

MPAI is indebted to the following individuals for their contributions to the development of Technical Specification – Neural Network Watermarking and Reference Software – Neural Network Watermarking: Carl De Sousa Trias and Mihai Mitrea.

Here are technical documents relevant to MPAI-NNW:

  1. MPAI-NNW Standard
  2. MPAI NNW Call for Technologies (closed)
  3. MPAI-NNW Use Cases and Functional Requirements
  4. MPAI-NNW Framework Licence
  5. MPAI-NNW Template for responses

Other relevant documents are:

MPAI-NNW standard

Users of MPAI standards should bear in mind the Notices and Disclaimers concerning use of MPAI Standards.

Version 1 Technical Specification Reference Software Specification Reference SW
Version 1.1 Reference Software Specification Reference SW

Visit the About MPAI-NNW page.

Contact the MPAI secretariat for more information.