Fighting Deepfakes Using Body Language Analysis

Abstract

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.

Multimodal Forgery Detection Using Ensemble Learning

“…Current video forgery detection methods mainly focus on behavior inconsistency, such as eye blinking [20], facial expression [21], head pose [22], lip movement [23], body motion [24], and mismatch between left and right eyes [25]. Obviously, most of these existing methods are unimodal methods using audio modality or visual modality.…”

Time-Series Neural Network: A High-Accuracy Time-Series Forecasting Method Based on Kernel Filter and Time Attention

“…In recent decades, many researchers and practitioners have tried to predict stock prices using various methods, including time-series-based prediction methods [7,8], machine learningbased prediction methods [9,10], deep learning-based prediction methods [11][12][13][14], and so on. However, due to the characteristics of stock prices, such as non-linearity, high noise, and variability, it is often difficult to achieve the desired prediction results with these methods [15][16][17][18][19][20][21].…”

Forecasting with Machine Learning Techniques

“…In the paper Fighting Deepfakes Using Body Language Analysis by Yasrab et al [9], the authors proposed a deepfake detection method using upper-body-language analysis. The approach used a many-to-one LSTM network that was designed and trained as a classification model for deepfake detection.…”