Exposing DeepFake Video Detection Based on Convolutional Long Short-Term Memory Network

Fig. 2. Influence of number of frames on the classification accuracy on the FaceForensics++ dataset. (a) Gaussian blur frame number; (b) face data removal frame number; (c) total frame number

Download full size

Table 1. Comparison of different backbone networks on the FaceForensics++ dataset
View table
Table 1. Comparison of different backbone networks on the FaceForensics++ dataset
Backbone network Classification accuracy /%
LQ HQ RAW
AlexNet^[22] 96.89 88.64 91.97
VGG16^[11] 90.85 92.35 94.67
ResNet^[10] 93.42 95.68 96.43
EfficientNet(Ours) 96.51 97.89 99.57

Table 2. Comparison of different algorithms on the FaceForensics++ dataset

View table

Table 2. Comparison of different algorithms on the FaceForensics++ dataset

Algorithm	Classification accuracy /%
Algorithm	LQ	HQ	RAW
CNN^[21]	90.00	91.45	93.40
SVM^[25]	70.10	73.64	75.43
RNN^[6]	93.46	95.04	95.98
GRU^[24]	94.48	96.18	97.54
LSTM^[14]	94.29	96.24	96.79
ConvLSTM^[19]	95.18	96.79	98.80
ConvLSTM(with attention)	96.51	97.89	99.57

Table 3. Experimental results of different attention models on the FaceForensics++ dataset
View table
Table 3. Experimental results of different attention models on the FaceForensics++ dataset
Model Classification accuracy /%
LQ HQ RAW
ConvLSTM 95.18 96.79 98.80
ConvLSTM+hard-attention 95.22 96.91 99.24
Self-attention 95.96 97.89 98.91
ConvLSTM+soft-attention 96.51 97.34 99.57

Table 4. Classification accuracy of the variation of Gaussian blur frame numbers on the FaceForensics++ dataset
View table
Table 4. Classification accuracy of the variation of Gaussian blur frame numbers on the FaceForensics++ dataset
Number of manipulatedframes Classification accuracy /%
LQ HQ RAW
2 71.32 78.41 82.17
3 85.66 87.63 89.68
4 88.97 90.05 92.53
5 92.65 94.32 97.43
6 75.74 79.57 82.64

Table 5. Experimental results of the facial data removal on the FaceForensics++ dataset
View table
Table 5. Experimental results of the facial data removal on the FaceForensics++ dataset
Number of manipulatedframes Classification accuracy /%
LQ HQ RAW
3 95.22 96.27 97.48
4 96.07 97.08 98.32
5 96.50 97.55 99.15
6 96.74 97.91 99.57
7 96.12 96.94 98.51
8 94.26 95.46 97.20
9 92.37 93.84 94.78

Table 6. Classification accuracy of the variation of the total frame numbers on the FaceForensics++ dataset
View table
Table 6. Classification accuracy of the variation of the total frame numbers on the FaceForensics++ dataset
Total framenumber Classification accuracy /%
LQ HQ RAW
5 93.43 95.06 95.95
10 96.51 97.32 98.22
15 96.70 98.49 99.91
20 96.74 98.08 99.05

Table 7. Comparison of classification experimental results of different algorithms on the FaceForensics++ dataset

View table

Table 7. Comparison of classification experimental results of different algorithms on the FaceForensics++ dataset

Reference	Method	Classifier	Classification accuracy /%	Dataset
Ref.[1]	Mesoscopic features	CNN	83.2	F2F
Ref.[21]	Steganalysis features	CNN	91.0	F2F
			94.0	DF
			93.0	FS
			81.0	NT
Ref.[6]	Temporal features	RNN	94.3	F2F
Ref.[27]	Temporal features	Optical Flow	81.6	F2F
Ref.[28]	Deep learning features	3DCNN	95.1	DF
Ref.[28]	Deep learning features	3DCNN	92.3	FS
This work	Interframe features	ConvLSTM	96.5	F2F
			96.7	DF
			94.9	FS
			92.7	NT

Tools

Get Citation

Copy Citation Text

Bowen Zheng, Huawei Xia, Ruidong Chen, Qiankun Han. Exposing DeepFake Video Detection Based on Convolutional Long Short-Term Memory Network[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2415002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Machine Vision

Received: Jan. 5, 2021

Accepted: Mar. 2, 2021

Published Online: Nov. 29, 2021

The Author Email: Xia Huawei (xiahuawei@tju.edu.cn), Chen Ruidong (20517610@qq.com), Han Qiankun (15822563807@163.com)

DOI:10.3788/LOP202158.2415002

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Comparison of different backbone networks on the FaceForensics++ dataset

Table 1. Comparison of different backbone networks on the FaceForensics++ dataset

Table 2. Comparison of different algorithms on the FaceForensics++ dataset

Table 2. Comparison of different algorithms on the FaceForensics++ dataset

Table 3. Experimental results of different attention models on the FaceForensics++ dataset

Table 3. Experimental results of different attention models on the FaceForensics++ dataset

Table 4. Classification accuracy of the variation of Gaussian blur frame numbers on the FaceForensics++ dataset

Table 4. Classification accuracy of the variation of Gaussian blur frame numbers on the FaceForensics++ dataset

Table 5. Experimental results of the facial data removal on the FaceForensics++ dataset

Table 5. Experimental results of the facial data removal on the FaceForensics++ dataset

Table 6. Classification accuracy of the variation of the total frame numbers on the FaceForensics++ dataset

Table 6. Classification accuracy of the variation of the total frame numbers on the FaceForensics++ dataset

Table 7. Comparison of classification experimental results of different algorithms on the FaceForensics++ dataset

Table 7. Comparison of classification experimental results of different algorithms on the FaceForensics++ dataset