Modular Convolutional Neural Network for Discriminating between Computer-Generated Images and Photographic Images

Huy H. Nguyen, Ngoc-Dung T. Tieu, Hoang-Quoc Nguyen-Son, Vincent Nozick, Junichi Yamagishi, Isao Echizen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Discriminating between computer-generated images (CGIs) and photographic images (PIs) is not a new problem in digital image forensics. However, with advances in rendering techniques supported by strong hardware and in generative adversarial networks, CGIs are becoming indistinguishable from PIs in both human and computer perception. This means that malicious actors can use CGIs for spoofing facial authentication systems, impersonating other people, and creating
fake news to be spread on social networks. The methods developed for discriminating between CGIs and PIs quickly become outdated and must be regularly enhanced to be able to reduce these attack surfaces. Leveraging recent advances in deep convolutional networks, we have built a modular CGI–PI discriminator with a customized VGG-19 network as the feature extractor, statistical convolutional neural networks as the feature transformers, and a discriminator. We also devised a probabilistic patch aggregation strategy to deal with high-resolution images. This proposed method outperformed a state-of-the-art method and achieved accuracy up to 100%.
Original languageEnglish
Title of host publication13th International Conference on Availability, Reliability and Security (ARES 2018)
Place of PublicationHamburg, Germany
PublisherACM
Pages1:1-1:10
Number of pages10
ISBN (Print)978-1-4503-6448-5
DOIs
Publication statusPublished - 27 Aug 2018
Event13th International Conference on Availability, Reliability and Security - Hamburg, Germany
Duration: 27 Aug 201830 Aug 2018
https://www.ares-conference.eu/conference-2018/cfp2018/

Conference

Conference13th International Conference on Availability, Reliability and Security
Abbreviated titleARES 2018
Country/TerritoryGermany
CityHamburg
Period27/08/1830/08/18
Internet address

Fingerprint

Dive into the research topics of 'Modular Convolutional Neural Network for Discriminating between Computer-Generated Images and Photographic Images'. Together they form a unique fingerprint.

Cite this