Deepfake detection using deeplearning

Deepfake detection using deeplearning
Author(s):
Kamla Vishwakarma , Prince Kori, Sushant Dhawane , Yogita Chavan
Keywords:
Res-next convolution neural network , RNN, LSTM (Long short-term memory)
Abstract
Increasing computing power has made deep learning algorithms so powerful that creating a fake video generated by artificial intelligence, popularly called as deep fakes, is very simple. Scenarios where this realistic face has been replaced by deep fakes are used to create political unrest, fake terrorist acts, revenge porn, blackmailing nations can easily be imagined. In this work, a new method is based on deep learning that can effectively distinguish fake videos generated by artificial intelligence from real videos. This method is able to automatically detect replacement and reenactment of deep forgery. Using artificial intelligence (AI) to fight against artificial intelligence (AI). This system uses Res-Next Convolution Neural Network to extract frame-level features and these features and further uses Long-Short-Term Memory (LSTM)-based Recurrent Neural Network (RNN) to classify whether the video is subject to some kind of manipulation or not, i.e. .whether the video is deepfake or real video. System can also achieve competitive results using a very simple and robust approach.
Article Details
Unique Paper ID: 159374 Publication Volume & Issue: Volume 9, Issue 11 Page(s): 981 - 984
Article Preview & Download

Share This Article

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org