AI-Powered Deepfake Detection Using CNN and Vision Transformer Architectures
🤖 AI Summary
This work proposes VFDNet, a novel architecture for detecting deepfake content that effectively integrates the lightweight MobileNetV3 with an efficient Vision Transformer mechanism. By incorporating strategic data preprocessing, augmentation, and transfer learning, VFDNet achieves high detection accuracy with low computational overhead on large-scale facial datasets. Experimental results demonstrate that the model attains state-of-the-art performance across multiple benchmark datasets, significantly enhancing generalization across diverse scenarios. These findings underscore VFDNet’s practical efficacy and efficiency in real-world applications, addressing the growing threat posed by deepfakes to digital authenticity.
Application Category
📝 Abstract
The increasing use of artificial intelligence-generated deepfakes creates major challenges in maintaining digital authenticity. Four AI-based models, consisting of three CNNs and one Vision Transformer, were evaluated using large face image datasets. Data preprocessing and augmentation techniques improved model performance across different scenarios. VFDNET demonstrated superior accuracy with MobileNetV3, showing efficient performance, thereby demonstrating AI's capabilities for dependable deepfake detection.
Problem
Research questions and friction points this paper is trying to address.
deepfake
digital authenticity
AI-generated content
face image manipulation
Innovation
Methods, ideas, or system contributions that make the work stand out.
Deepfake detection
Convolutional Neural Network
Vision Transformer
MobileNetV3
Data augmentation
🔎 Similar Papers
No similar papers found.
