• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Cascaded-Hop For DeepFake Videos Detection

Vol. 16, No. 5, May 31, 2022
10.3837/tiis.2022.05.014, Download Paper (Free):


Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.


Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.

Cite this article

[IEEE Style]
D. Zhang, P. Wu, F. Li, W. Zhu and V. S. Sheng, "Cascaded-Hop For DeepFake Videos Detection," KSII Transactions on Internet and Information Systems, vol. 16, no. 5, pp. 1671-1686, 2022. DOI: 10.3837/tiis.2022.05.014.

[ACM Style]
Dengyong Zhang, Pengjie Wu, Feng Li, Wenjie Zhu, and Victor S. Sheng. 2022. Cascaded-Hop For DeepFake Videos Detection. KSII Transactions on Internet and Information Systems, 16, 5, (2022), 1671-1686. DOI: 10.3837/tiis.2022.05.014.

[BibTeX Style]
@article{tiis:25676, title="Cascaded-Hop For DeepFake Videos Detection", author="Dengyong Zhang and Pengjie Wu and Feng Li and Wenjie Zhu and Victor S. Sheng and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2022.05.014}, volume={16}, number={5}, year="2022", month={May}, pages={1671-1686}}