Table 5 Robustness of different methods
From: A video coverless information hiding algorithm based on semantic segmentation
DAVIS | ||||
|---|---|---|---|---|
Attack | Ours | Zheng [13] | Zhou [6] | Zhang [9] |
Salt and pepper (σ = 0.001) | 0.8332 | 0.9436 | 0.9983 | 0.9982 |
Salt and pepper (σ = 0.005) | 0.6169 | 0.9028 | 0.9967 | 0.9969 |
Gauss (σ = 0.001) | 0.3055 | 0.7480 | 0.9693 | 0.9645 |
Gauss (σ = 0.005) | 0.2975 | 0.7483 | 0.9703 | 0.9653 |
Speckle (σ = 0.01) | 0.4959 | 0.8374 | 0.9780 | 0.9793 |
Speckle (σ = 0.05) | 0.3002 | 0.6887 | 0.9294 | 0.9370 |
JPEG (σ = 70) | 0.7717 | 0.9149 | 0.9912 | 0.9962 |
JPEG (σ = 90) | 0.8833 | 0.9439 | 0.9935 | 0.9983 |