Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance
1 Functions
The Post-Training Watermark Insertion (NNW-PWI) AIM provides the Watermarked model in response to the Unwatermarked model of a trained neural network and a given Payload. It does not train the neural network. The Watermarked model is a new ML Model Object, of the same format and Qualifier as the Unwatermarked model. The AIM also gives the Locator: the method that inserted the watermark and, where the method states them, the tensors that carry it. Where the Payload does not fit, or the format of the model is not one that its Implementation supports, the AIM gives neither and reports why.
2 Reference Model
3 Input/Output Data
Table 1 specifies the Input and Output Data of the Post-Training Watermark Insertion (NNW-PWI) AIM.
Table 1 – I/O Data of the Post-Training Watermark Insertion (NNW-PWI)
| Input | Acronyms | Descriptions |
| Unwatermarked model | AIP-MLO | The trained neural network model in which the Payload is to be inserted. |
| Payload | NNW-PLD | The information to be inserted in the neural network. |
| Output | Acronyms | Descriptions |
| Watermarked model | AIP-MLO | The neural network model with the Payload inserted. |
| Locator | NNW-WLC | Where the watermark sits in the model and the method that inserted it. |
4 SubAIMs
No SubAIMs.
5 JSON Metadata
https://schemas.mpai.community/NNW1/V1.2/AIMs/PostTrainingWatermarkInsertion.json
6 Profiles
No profiles.
