Abstract: The growing computation power has made the deep learning algorithms so powerful that creating an indistinguishable human synthesized image popularly called as deep fakes have become very simple. Scenarios where this realistic face swapped deepfake are used to create political distress, fake terrorism events, revenge porn, blackmail people are easily envisioned. In this project, System will detect fake images that have been generated using AI. Deep Fakes are created by using deep learning techniques and neural networks to manipulate or replace parts of an original image, such as the face of a person.
This project is an important application of deep learning technology, which is characterized by its strong capability of feature learning and feature representation compared with the traditional image detection methods. System will describe a new deep learning-based method that can effectively distinguish AI-generated fake images from real images. System is capable of automatically detecting the replacement, reenactment deep fakes and trying to use Artificial Intelligence (AI) to fight Artificial Intelligence (AI). Our system uses a Res-Next Convolution Neural Network to extract frame-level features and these features and further train a Convolutional Neural Network (CNN) based InceptionResnetV1 and InceptionResnetV2 to classify whether the image is subject to any Type manipulation or not, i.e. image is deep fake or real image. It will allow us to detect deep fake images and can further help in reducing fake news.
Keywords: Deep Learning, Deepfake, Neural Network, Artificial Intelligence, InceptionResnetV1, InceptionResnetV2
Cite:
Mr. H.M. Gaikwad, Aryan Sonawane, Manavaditya Rathawa, Ratnali Pawar, Uday Talele, "Deepfake Face Detection System ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13359.
|
DOI:
10.17148/IJARCCE.2024.13359
