Preprint Article Version 2 Preserved in Portico This version is not peer-reviewed

Fighting Deepfakes Using Body Language Analysis

Version 1 : Received: 15 March 2021 / Approved: 16 March 2021 / Online: 16 March 2021 (11:02:45 CET)
Version 2 : Received: 28 April 2021 / Approved: 28 April 2021 / Online: 28 April 2021 (12:02:00 CEST)

A peer-reviewed article of this Preprint also exists.

Yasrab, R.; Jiang, W.; Riaz, A. Fighting Deepfakes Using Body Language Analysis. Forecasting 2021, 3, 303-321. Yasrab, R.; Jiang, W.; Riaz, A. Fighting Deepfakes Using Body Language Analysis. Forecasting 2021, 3, 303-321.


Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes.


Imaging; Machine learning; Deepfakes; Human pose estimation; Upper body languages; World leader; Deep learning; Computer vision; Recurrent Neural Networks (RNNs); Long Short-term Memory(LSTM); machine learning; Forecasting


Computer Science and Mathematics, Algebra and Number Theory

Comments (1)

Comment 1
Received: 28 April 2021
Commenter: Robail Yasrab
Commenter's Conflict of Interests: Author
Comment: Citation issues resolved. It was issued with capital letters. Referenced as “cao2018openpose” & “cao2019openpose”, But it should be cao2018OpenPose and cao2019OpenPose. I have changed it. Now no more missing citations. (Page 3,6,7) Page 9, Table 2. Changed the BOLD table entries to normal (as suggested). Issues with Table 5 reference is resolved. Table 4 also mentioned in the text. (page 14) Table 3, Bold heading is necessary for 3rd Table 4 bold heading is removed. Table 5 Bold entries are removed. Table 6 Bold entries are removed. Reference 7, Weblink, and date added. The issues between citations 18 and 39 resolved. It's a same-titled publication. One published as conference processing and later an extended version published in Journal. Required Information added in Reference 24 Required Information added in Reference 38
+ Respond to this comment

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 1
Metrics 0

Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.