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.

Watch the video and the presentation:

YouTube video Non-YouTube 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:

Visit the About MPAI-NNW page.

Contact the MPAI secretariat for more information.