Team Members

Zeina Ayman

Team Leader

Natalie Sherif

Team Member

Mariam Mohamed

Team Member

Mohamed Hazem

Team Member

Supervisors

Dr. Diaa Salama AbdElminaam

Associate Professor

Eng. Samira Refaat Kamal

Teaching Assistant

Abstract

The main idea of this project is to develop a web application that can help to detect whether the input data we provide of people whether celebrities or people in general are real or fake and generate deepfakes itself. Recently with the evolution of technology and with advanced image editing tools, people can easily get manipulated, as deepfake algorithms can easily create fake videos and images that people can’t distinguish from authentic ones, which is an emerging problem threatening the trustworthiness of online information. Deepfakes mainly affect public figures, celebrities, and politicians. Forged videos are videos that contain fake images over real ones and in this research, there are methods used with Machine and deep learning approaches that will be used with the dataset that is composed of deep fake videos and authentic ones to detect these manipulations and protect the government from criminals and there will be various techniques used to distinguish real from fake using face swapping or is there something off regarding it’s behaviour, or if a voice of a person is used with another person’s voice , etc. The deep fake detector can be used in courts and police stations to reduce the likelihood of crimes and frauds that may happen and detect them. This project aims to make a website to detect whether videos are fake or not. More and above the website will also provide a deepfake generation.

System Objectives

1. Provide a user-friendly and simple website that could be easily accessed by the users and fulfill their needs.

2. Provide precise, more accurate deepfake detection.

3. Generates a deepfake that the user desires.

4. Result (fake or real) will be obtained based on the dataset entered.

System Scope

• The system has two main features, one for the deepfake detection and the other for the deepfake generation.

• Deep-learning methods are used in the system as CNN in order to train the dataset used.

• The website is expected to inform the user whether the content is fake or real.

• The website is expected to generate a deepfake video.

• Pre-processing is done to extract faces from videos and images.

Documents and Presentations

Proposal

You will find here the documents and presentation for our proposal.

Document

Presentation

SRS

You will find here the documents and presentation for our SRS.

Document

presentation

SDD

You will find here the documents and presentation for our SDD.

Document

presentation

Thesis

You will find here the documents and presentation for our Thesis

Document

Presentation

Accomplishments

Publications

Competitions

Competition Title

type here detailss about your participation in the competition.