Provides the means to establish a standard setting to measure the performance of a Watermarked Neural Network. What MPAI-NNW is about
Description of MPAI-NNW
Technical Specification  Reference Software V1.2 (code)

What MPAI-NNW is about

Technical Specification: Neural Network Watermarking (MPAI-NNW) V1.0  provides the means to measure, for a given size of the watermarking payload, the ability of the watermark:

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

Material about MPAI-NNW

MPAI is indebted to the following individuals for their contributions to the development of

  • Technical Specification: Neural Network Watermarking: Carl De Sousa Trias and Mihai Mitrea.
  • Reference Software Specification: Neural Network Watermarking: Alessandro Carra, Carl de Sousa Trias, Gérard Chollet, and Mihai Mitrea.

Here are technical documents relevant to MPAI-NNW:

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

MPAI appreciates the work carried out by Alessandro Carra, Mihai Mitrea and Carl de Sousa Trias in the development of Reference Software Specification: Neural Network Watermarking (MPAI-NNW) V1.2.

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.