Abstract :

The Rapid Progression Of Artificial Intelligence Has Led To The Development Of Deepfake Systems Capable Of Generating Highly Realistic, Artificially Manipulated Media In The Form Of Images, Videos, Audio, And Text. These Synthetic Materials Pose A Significant Threat To Digital Security, The Control Of Misinformation, And The Verification Of Media Authenticity. This Paper Presents A Multimodal Deepfake Detection System Capable Of Identifying Manipulated Content Across Various Formats, Including Images, Videos, Audio, And Text Data. The Proposed Framework Utilizes A Hybrid Deep Learning Approach, Combining Convolutional Neural Networks (CNN) And Long Short-Term Memory (LSTM) Networks, To Detect Deepfake Faces In Both Images And Videos. For Audio Deepfake Detection, Mel-Frequency Cepstral Coefficient (MFCC) Features Are Extracted And Fed Into A Trained Deep Learning Network. Additionally, Term Frequency–Inverse Document Frequency (TF-IDF) Vectorization, Along With A Logistic Regression Classifier, Is Used To Detect Fake Textual Content. The System Is Implemented In Python, With A Graphical User Interface Developed Using Tkinter To Enable Easy Interaction And Media Analysis. Experimental Results Indicate That The Proposed System Effectively Identifies Deepfake Media By Analysing Spatial, Temporal, And Linguistic Patterns. Furthermore, The Solution Contributes To Enhancing Digital Content Analysis And Mitigating The Spread Of Manipulated Information On The Internet.

Published:

16-6-2026

Issue:

Vol. 26 No. 6 (2026)

Page Nos:

1132-1137

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite