Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection

Saravana Balaji Balasubramanian; Jagadeesh Kannan R; Prabu P; Venkatachalam K; Pavel Trojovský

doi:10.7717/peerj-cs.1040

Deep fake detection using cascaded deep sparse auto-encoder for effective feature selection

PeerJ Comput Sci. 2022 Jul 13:8:e1040. doi: 10.7717/peerj-cs.1040. eCollection 2022.

Authors

Saravana Balaji Balasubramanian¹, Jagadeesh Kannan R², Prabu P³, Venkatachalam K⁴, Pavel Trojovský⁵

Affiliations

¹ Department of Information Technology, Lebanese French University, Erbil, Iraq.
² School of Computer Science and Engineering, VIT Chennai, Chennai, Tamilnadu, India.
³ Department of Computer Science, CHRIST (Deemed to be University), Bangalore, Karnataka, India.
⁴ Department of Applied Cybernetics, University of Hradec Králové, Hradec Kralove, Czech Republic.
⁵ Department of Mathematics, University of Hradec Králové, Hradec Kralove, Czech Republic.

Abstract

In the recent research era, artificial intelligence techniques have been used for computer vision, big data analysis, and detection systems. The development of these advanced technologies has also increased security and privacy issues. One kind of this issue is Deepfakes which is the combined word of deep learning and fake. DeepFake refers to the formation of a fake image or video using artificial intelligence approaches which are created for political abuse, fake data transfer, and pornography. This paper has developed a Deepfake detection method by examining the computer vision features of the digital content. The computer vision features based on the frame change are extracted using a proposed deep learning model called the Cascaded Deep Sparse Auto Encoder (CDSAE) trained by temporal CNN. The detection process is performed using a Deep Neural Network (DNN) to classify the deep fake image/video from the real image/video. The proposed model is implemented using Face2Face, FaceSwap, and DFDC datasets which have secured an improved detection rate when compared to the traditional deep fake detection approaches.

Keywords: DNN; Deep fake detection; Deep learning; Deep sparse Auto encoder; Face2Face; FaceSwap; Faceforensics++; Temporal Convolutional neural network.

Grants and funding

This research was funded by the Project of Excellence of Faculty of Science, University of Hradec Králové, grant number 2210/2022-2023. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.