Home / Current Issue / Paper 1707875
Deepfake Detection Using Machine Learning
Subject area: Science,Engineering and Technology · Area of research: Computer Science And Engineering
Abstract
Deepfake detection has become increasingly challenging due to advancements in computational power and deep learning algorithms. The creation of highly realistic AI-generated videos, commonly known as deepfakes, poses significant threats, including political unrest, fake terrorism events, revenge porn, and blackmail. This work introduces a novel deep learning-based approach to effectively distinguish AI-generated fake videos from real ones. The proposed system combines a ResNeXt convolutional neural network to extract frame-level features with a Long Short-Term Memory (LSTM) recurrent neural network for video classification. It identifies manipulations such as face replacements and reenactments in videos. To enhance real-world performance, the model is trained and evaluated on a diverse, balanced dataset that integrates multiple sources, including FaceForensics++, the Deepfake Detection Challenge, and Celeb-DF. This straightforward yet robust method demonstrates competitive results in combating deepfake threats using AI.
Keywords
Deepfake Detection, ResNeXt, LSTM, Artificial Intelligence, Video Manipulation, Face Replacement, Reenactment, Convolutional Neural Network, Recurrent Neural Network, FaceForensics++, Celeb-DF, AI-Generated Videos.
References
[1] Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies,Matthias Nießner, “FaceForensics++: Learning to Detect Manipulated Facial Images” in arXiv:1901.08971.
[2] Deepfake detection challenge dataset : https://www.kaggle.com/c/deepfake-detection challenge/data Accessed on 26 March, 2024
[3] Yuezun Li , Xin Yang , Pu Sun , Honggang Qi and Siwei Lyu “Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics” in arXiv:1909.12962.
[4] Deepfake Video of Mark Zuckerberg Goes Viral on Eve of House A.I. Hearing : https://fortune.com/2019/06/12/deepfake-mark-zuckerberg/ Accessed on 26 March, 2024
[5] 10 deepfake examples that terrified and amused the internet: https://www.creativebloq.com/features/deepfake-examples Accessed on 26 March, 2024
[6] TensorFlow: https://www.tensorflow.org/ (Accessed on 26 March, 2024)
[7] Keras: https://keras.io/ (Accessed on 26 March, 2024)
[8] PyTorch : https://pytorch.org/ (Accessed on 26 March, 2024)
[9] G. Antipov, M. Baccouche, and J.-L. Dugelay. Face aging with conditional gen erative adversarial networks. arXiv:1702.01983, Feb. 2017
[10] J. Thies et al. Face2Face: Real-time face capture and reenactment of rgb videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2387–2395, June 2016. Las Vegas, NV.
[11] Face app: https://www.faceapp.com/ (Accessed on 26 March, 2024)
[12] Face Swap : https://faceswaponline.com/ (Accessed on 26 March, 2024)
[13] hËmƒh^~ 6�OJQJ]�hËmƒhJFÉ6�OJQJ]�hËmƒhËmƒ6�H*OJQJ]�hËmƒhJFÉ6�H*OJQJ]�hê*H*OJQJhŠX6OJQJhËmƒOJQJhJFÉOJQJhJFÉOJPJQJh^~ h^~ OJPJQJh^~ h^~ H*OJQJh5.OJPJQJh^~ h^~ OJQJhJFÉCJ(OJPJQJhËmƒCJ(OJPJQJhJFÉhËmƒCJ(OJPJQJ*+o�ÌÍÎäåÌ [Some characters in this reference could not be displayed correctly — please refer to the published PDF for the full reference.]
[14] [Some characters in this reference could not be displayed correctly — please refer to the published PDF for the full reference.]
How to cite this paper
@article{1707875,
author = {Neelakantan J, C Lakshith Appaiah, Rohithashwa R, Prof. Pooja A},
title = {Deepfake Detection Using Machine Learning},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {8},
number = {10},
pages = {515-518},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1707875.pdf},
abstract = {Deepfake detection has become increasingly challenging due to advancements in computational power and deep learning algorithms. The creation of highly realistic AI-generated videos, commonly known as deepfakes, poses significant threats, including political unrest, fake terrorism events, revenge porn, and blackmail. This work introduces a novel deep learning-based approach to effectively distinguish AI-generated fake videos from real ones. The proposed system combines a ResNeXt convolutional neural network to extract frame-level features with a Long Short-Term Memory (LSTM) recurrent neural network for video classification. It identifies manipulations such as face replacements and reenactments in videos. To enhance real-world performance, the model is trained and evaluated on a diverse, balanced dataset that integrates multiple sources, including FaceForensics++, the Deepfake Detection Challenge, and Celeb-DF. This straightforward yet robust method demonstrates competitive results in combating deepfake threats using AI.},
keywords = {Deepfake Detection, ResNeXt, LSTM, Artificial Intelligence, Video Manipulation, Face Replacement, Reenactment, Convolutional Neural Network, Recurrent Neural Network, FaceForensics++, Celeb-DF, AI-Generated Videos.},
month = {April},
}