IEEE - P3304/D1
Draft Standard Adoption of Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) Technical Specification Neural Network Watermarking (MPAI-NNW) V1
| Organization: | IEEE |
| Publication Date: | 1 May 2022 |
| Status: | pending |
| Page Count: | 24 |
scope:
Scope of Standard
MPAI-NNW specifies methodologies to evaluate the following aspects of a neural network watermarking technology:
• The impact on the performance of a watermarked neural network and its inference.
• The ability of a neural network watermarking detector/decoder to detect/decode a payload when the watermarked neural network has been modified.
• The computational cost of injecting, detecting, or decoding a payload in the watermarked neural network.
The standard assumes that:
• The neural network watermarking technology to be evaluated according to this standard is publicly available.
• The watermarking key is unknown during evaluation.
• The performance of the neural network watermarking technology does not depend on a specific key.
This Technical Specification has been developed by the MPAI Neural Network Watermarking Development Committee (NNW-DC). As the neural network watermarking area is fast-evolving, MPAI expects it will produce future MPAI-NNW versions providing methods to cope with technology evolution.
Document History