Deepfake Detection of Face Images based on a Convolutional Neural Network

2025-03-14

AI Summary

Deepfake technology poses escalating threats to political figures and public security. To address this challenge, this paper proposes a lightweight face forgery detection framework designed to generalize across diverse deepfake generation methods. Building upon ResNet-50, we employ fine-grained transfer learning and end-to-end fine-tuning to construct a binary-classification CNN with a single-neuron output, enabling image-level authenticity assessment. Our key contribution is a unified detection architecture that significantly enhances cross-algorithm generalization—particularly against state-of-the-art forgery techniques such as StyleGAN and FaceFusion. Evaluated on the Diverse Face Fake dataset, the model achieves 98% accuracy, 96% recall, 97% F1-score, and an AUC of 0.99. The framework balances high detection performance with computational efficiency, ensuring practical deployability in real-world forensic and monitoring systems.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Fake News and especially deepfakes (generated, non-real image or video content) have become a serious topic over the last years. With the emergence of machine learning algorithms it is now easier than ever before to generate such fake content, even for private persons. This issue of generated fake images is especially critical in the context of politics and public figures. We want to address this conflict by building a model based on a Convolutions Neural Network in order to detect such generated and fake images showing human portraits. As a basis, we use a pre-trained ResNet-50 model due to its effectiveness in terms of classifying images. We then adopted the base model to our task of classifying a single image as authentic/real or fake by adding an fully connected output layer containing a single neuron indicating the authenticity of an image. We applied fine tuning and transfer learning to develop the model and improve its parameters. For the training process we collected the image data set"Diverse Face Fake Dataset"containing a wide range of different image manipulation methods and also diversity in terms of faces visible on the images. With our final model we reached the following outstanding performance metrics: precision = 0.98, recall 0.96, F1-Score = 0.97 and an area-under-curve = 0.99.

Problem

• Detect deepfake images using Convolutional Neural Networks.
• Address fake image issues in politics and public figures.
• Improve model performance with fine-tuning and transfer learning.

Innovation

• Convolutional Neural Network for deepfake detection
• ResNet-50 model with added fully connected layer
• Fine tuning and transfer learning for model improvement