Table 22 and Table 23 provide samples of the performance of three Neural Network Traceability technologies measured in Section 7 of this standard.
Table 22 provides samples of Imperceptibility results, with α (the epoch of insertion for NCT), N (the number of marked parameters for NCT), λ (hyperparameter of RTW), and ρ (hyperparameter of TBW).
Table 23 provides the results for Computational Cost.
Concerning the Robustness evaluation, all methods show that the mark can be extracted before the performance of the Modified models drops.
Table 22 and Table 23 represent snapshots capturing the state-of-the-art of the general procedure and of performance of implementations. This NNT-TEC will be updated to reflect the evolution of Traceability Technologies.
Table 22 Samples of Imperceptibility results.
| Method | Model | Parameter | Relative variation of the classification error |
| NCT | VGG16 | N=64, α=0 | 0 |
| N=16144, α=90 | 1 | ||
| ResNet8 | N=64, α=0 | 0 | |
| N=16144, α=90 | 192 | ||
| RTW | VGG16 | λ= 0.01 | 2 |
| ResNet8 | λ= 0.01 | 5 | |
| TBW | VGG16 | Rho = 10 | 7 |
| ResNet8 | Rho = 10 | 7 |
Table 23 Samples of Computational Cost results.
| Method | Average number of batch iterations to insert the mark | Increased batch iteration time (%) |
| NCT | 0 | 0 |
| RTW | 500 | 16.64 |
| TBW | 504 | 62.69 |
