From: Assessment framework for deepfake detection in real-world situations
Methods | TrainSet | Compression | Brightness | Grayscale | Contrast | Flipping | Resolution | Gaussian Noise | Vintage Filter | Overall Average | ||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 |  | C23 | C40 | Increase | Decrease |  |  | Horizontal | Vertical | x2 | x4 |  |  |  |
CapsuleNet | FFpp- Raw | 77.97 | 54.14 | 73.31 | 70.62 | 68.38 | 69.31 | 73.13 | 63.20 | 65.43 | 56.99 | 54.14 | 72.94 | 66.63 |
+SDAug | 92.76 | 72.32 | 89.56 | 89.50 | 88.17 | 89.93 | 89.40 | 62.61 | 78.55 | 74.93 | 81.86 | 85.21 | 82.90 | |
XceptionNet | 69.49 | 55.70 | 65.92 | 66.40 | 65.51 | 65.32 | 65.26 | 57.36 | 57.23 | 55.90 | 50.50 | 66.90 | 61.79 | |
+SDAug | 94.89 | 80.53 | 93.36 | 93.05 | 92.64 | 92.98 | 92.32 | 57.65 | 88.42 | 81.60 | 88.91 | 90.47 | 87.24 | |
SBIs | 90.43 | 76.27 | 86.38 | 86.47 | 86.27 | 85.94 | 85.98 | 79.28 | 76.35 | 63.62 | 71.52 | 86.54 | 81.25 | |
+SDAug | 89.31 | 76.60 | 85.55 | 86.24 | 85.41 | 84.76 | 85.48 | 78.67 | 77.06 | 64.31 | 77.13 | 86.11 | 81.39 |