Generative Adversarial Networks for Deepfake Generation

Location

Russell Student Union, Statesboro Campus- Room 2052

Document Type and Release Option

Thesis Presentation (Restricted to Georgia Southern)

Faculty Mentor

Dr. Hayden Wimmer

Faculty Mentor Email

hwimmer@georgiasouthern.edu

Presentation Year

2021

Start Date

17-11-2021 7:05 PM

End Date

17-11-2021 8:05 PM

Keywords

Georgia Southern University, Honors College, Honors Symposium, Presentation

Description

Deep learning is a type of Artifcial Intelligence that mimics the workings of the human brain in processing data such as speech recognition, object detection, and making decisions. Deepfakes are a machine learning technique where a person in an existing image or video is replaced by someone else’s likeness. In this project we develop a Generative Adversarial Network to generate deepfakes and develop a survey to determine if participants can identify authentic versus deepfake images.

Academic Unit

Allen E. Paulson College of Engineering and Computing

Comments

This work is archived and distributed under the repository's standard copyright and reuse license, available here. Under this license, end-users may copy, store, and distribute this work without restriction. For questions related to additional reuse of this work, please contact the copyright owner.

This document is currently not available here.

Share

COinS
 
Nov 17th, 7:05 PM Nov 17th, 8:05 PM

Generative Adversarial Networks for Deepfake Generation

Russell Student Union, Statesboro Campus- Room 2052

Deep learning is a type of Artifcial Intelligence that mimics the workings of the human brain in processing data such as speech recognition, object detection, and making decisions. Deepfakes are a machine learning technique where a person in an existing image or video is replaced by someone else’s likeness. In this project we develop a Generative Adversarial Network to generate deepfakes and develop a survey to determine if participants can identify authentic versus deepfake images.