Deepfake Video Detection using EfficientNet and CNN-LSTM Architecture

View at publisher Summarise with VIRAT
Authors: RajeshKannan T, Rev M Dr. Nisha, Ramarathinam M, Dr. Kumanan T, Moulidharan AD
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Deepfake videos generated using advanced artificial intelligence techniques have become increasingly realistic and pose serious threats to digital media authenticity and public trust. Detecting manipulated videos is therefore an important challenge in modern computer vision research. Many existing deepfake detection approaches analyze complete video frames using complex deep learning models, which increasescomputational cost and processing time. To address this issue, this work proposes a deepfake video detection approachthatfocuses mainly on facial regions, sincemostdeepfakemanipulationsoccurontheface.DeepfakeDetection,DeepLearning,onvolutionalNeural Network (CNN), EfficientNet, Face Detection, Frame Extraction, Facial Feature Analysis, Video Manipulation Detection, Image Processing, Artificial Intelligence

Fields of Study & Subjects

Digital Media Forensic Detection Generative Adversarial Networks and Image Synthesis Misinformation and Its Impacts

Publication details

Journal / source
International Scientific Journal of Engineering and Management
Volume
05
Issue
03
Pages
1–9
Publication date
22 March 2026
Language
EN