Detecting Forged Images with Machine Learning

Document Type

Oral Presentation

Campus where you would like to present

Ellensburg

Event Website

https://digitalcommons.cwu.edu/source

Start Date

18-5-2020

Abstract

The issue of forged images is now a global problem which mainly spreads via social network. Image forgery has weakened people's confidence in digital photos. Many researchers have devoted extensive research contributions in recent years to the development of new techniques to combat various image forgery attacks. Automatically detecting fake images may protect people from being victims of forged photos that can deceive and cause harm to others. Our contribution is a hybrid method which combines Error Level Analysis and deep learning for detecting manipulated images. According to our preliminary experimental results, the combination of image pre-processing and machine learning techniques is an efficient approach detecting image forgery attacks.

Faculty Mentor(s)

Razvan Andonie

Department/Program

Computer Sciences

Additional Mentoring Department

https://cwu.studentopportunitycenter.com/2020/04/detecting-forged-images-with-machine-learning/

Share

COinS
 
May 18th, 12:00 PM

Detecting Forged Images with Machine Learning

Ellensburg

The issue of forged images is now a global problem which mainly spreads via social network. Image forgery has weakened people's confidence in digital photos. Many researchers have devoted extensive research contributions in recent years to the development of new techniques to combat various image forgery attacks. Automatically detecting fake images may protect people from being victims of forged photos that can deceive and cause harm to others. Our contribution is a hybrid method which combines Error Level Analysis and deep learning for detecting manipulated images. According to our preliminary experimental results, the combination of image pre-processing and machine learning techniques is an efficient approach detecting image forgery attacks.

https://digitalcommons.cwu.edu/source/2020/COTS/42