Neural Network Watermarking

Neural Network Watermarking (NNW) is a project developing requirements for a standard enabling, for a given size of the watermarking payload, the measure of:

  1. The impact, e.g., the degradation of the user experience caused by the watermark applied to a neural network.
  2. The resistance to attacks, e.g., transfer learning, pruning.
  3. The processing cost of watermarking injection, e.g., time, processing cost.

Relevant documents are:

Visit the About MPAI-NNW page.

As this is MPAI activity targets the development of use cases and functional requirements of neural network watermarking, its is open to non MPAI members. Contact the MPAI secretariat for more information.