DeepAI AI Chat
Log In Sign Up

Preliminary Forensics Analysis of DeepFake Images

04/27/2020
by   Luca Guarnera, et al.
University of Catania
13

One of the most terrifying phenomenon nowadays is the DeepFake: the possibility to automatically replace a person's face in images and videos by exploiting algorithms based on deep learning. This paper will present a brief overview of technologies able to produce DeepFake images of faces. A forensics analysis of those images with standard methods will be presented: not surprisingly state of the art techniques are not completely able to detect the fakeness. To solve this, a preliminary idea on how to fight DeepFake images of faces will be presented by analysing anomalies in the frequency domain.

READ FULL TEXT

page 1

page 4

page 5

05/15/2018

Learning to Deblur Images with Exemplars

Human faces are one interesting object class with numerous applications....
10/03/2019

Vulnerability of Face Recognition to Deep Morphing

It is increasingly easy to automatically swap faces in images and video ...
01/08/2018

Identity-preserving Face Recovery from Portraits

Recovering the latent photorealistic faces from their artistic portraits...
11/08/2021

A Study of the Human Perception of Synthetic Faces

Advances in face synthesis have raised alarms about the deceptive use of...
06/14/2021

More Real than Real: A Study on Human Visual Perception of Synthetic Faces

Deep fakes became extremely popular in the last years, also thanks to th...
04/03/2013

A software for aging faces applied to ancient marble busts

The study and development of software able to show the effect of aging o...
04/02/2019

SafeAccess: Towards a Dialogue Enabled Access to the Smart Home for the Friends and Families

SafeAccess is an interactive assistive technology solution to enhance th...