Deepfake Detection Using Machine Learning

• Author(s): Neelakantan J ; C Lakshith Appaiah ; Rohithashwa R ; Prof. Pooja A
• Paper ID: 1707875
• Page: 515-518
• Published Date: 14-04-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 8 Issue 10 April-2025

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.

Citations

IRE Journals:
Neelakantan J , C Lakshith Appaiah , Rohithashwa R , Prof. Pooja A "Deepfake Detection Using Machine Learning" Iconic Research And Engineering Journals Volume 8 Issue 10 2025 Page 515-518

IEEE:
Neelakantan J , C Lakshith Appaiah , Rohithashwa R , Prof. Pooja A "Deepfake Detection Using Machine Learning" Iconic Research And Engineering Journals, 8(10)