Neural Network Watermarking

Neural Network Watermarking is an MPAI project Neural Network Watermarking (NNW) targeting a 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 is developing the Technical Specification using the submissions received in response to its call for technologies:

  1. Technical Specification – Neural Network Watermarking (MPAI-NNW) V1
  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.

As this is MPAI activity is now expecting to receive submissions in response to the Call for Technologies, and until responses are assessed, its meetings are  open to non MPAI members. Contact the MPAI secretariat for more information.