View Proposal

---

Proposer

Nurul Ain Toha

Title

Real and Fake Face Images Detection using Machine Learning

Goal

Uses machine learning model to detect real and fake images

Description

This project focuses on developing a machine learning model to accurately detect real and fake face images using the "Real and Fake Face Detection" dataset from Yonsei University on Kaggle. With the rise of deepfake technology, which creates hyper-realistic synthetic faces through methods like GANs (Generative Adversarial Networks), this project aims to build a model that can distinguish between authentic and AI-generated faces. The model will utilize deep learning, specifically Convolutional Neural Networks (CNNs), and transfer learning techniques to enhance performance. By addressing the growing need for digital media authenticity, the project contributes to combating the misuse of AI in generating fake images.

Resources

(1) Atwan, J., et al., 2024. Using Deep Learning to Recognize Fake Faces. International Journal of Advanced Computer Science and Applications (IJACSA), 15(1). https://doi.org/10.14569/IJACSA.2024.01501113. (2) Rafque, R., et al., 2023. Deep fake detection and classification using error‑level analysis and deep learning. Scientific Reports, 13, p.7422. https://doi.org/10.1038/s41598-023-34629-3. (3) Eldien, N.A.S., et al., 2023. Real and Fake Face Detection: A Comprehensive Evaluation of Machine Learning and Deep Learning Techniques for Improved Performance. 2023 Intelligent Methods, Systems, and Applications (IMSA), pp.315-320. https://doi.org/10.1109/IMSA58542.2023.10217736. (4) Chandani, K. and Arora, M., 2021. Automatic Facial Forgery Detection Using Deep Neural Networks. In: Advances in Interdisciplinary Engineering. Lecture Notes in Mechanical Engineering. Springer, Singapore. https://doi.org/10.1007/978-981-15-9956-9_21. (5) Computational Intelligence and Photography Lab, Yonsei University, Real and Fake Face Detection dataset, [2041 images], publicly available at Yonsei University’s Computational Intelligence and Photography Lab. https://www.kaggle.com/datasets/ciplab/real-and-fake-face-detection/data

Background

Url

External Link

Difficulty Level

Moderate

Ethical Approval

Full

Number Of Students

1

Supervisor

Nurul Ain Toha

Keywords

Degrees

Bachelor of Science in Statistical Data Science