Security and forensics exploration of learning-based image coding

Deepayan Bhowmik, Mohamed Elawady, Keiller Nogueira

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

4 Downloads (Pure)

Abstract

Advances in media compression indicate significant potential to drive future media coding standards, e.g., Joint Photographic Experts Group's learning-based image coding technologies (JPEG AI) and Joint Video Experts Team's (JVET) deep neural networks (DNN) based video coding. These codecs in fact represent a new type of media format. As a dire consequence, traditional media security and forensic techniques will no longer be of use. This paper proposes an initial study on the effectiveness of traditional watermarking on two state-of-the-art learning based image coding. Results indicate that traditional watermarking methods are no longer effective. We also examine the forensic trails of various DNN architectures in the learning based codecs by proposing a residual noise based source identification algorithm that achieved 79% accuracy.
Original languageEnglish
Title of host publication2021 International Conference on Visual Communications and Image Processing (VCIP)
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages1-5
Number of pages5
ISBN (Electronic)9781728185514
ISBN (Print)9781728173221
DOIs
Publication statusPublished - 19 Jan 2022
Externally publishedYes
Event2021 International Conference on Visual Communications and Image Processing (VCIP) - Munich, Germany
Duration: 5 Dec 20218 Dec 2021

Publication series

NameIEEE International Conference on Visual Communications and Image Processing (VCIP)
PublisherIEEE
ISSN (Print)1018-8770
ISSN (Electronic)2642-9357

Conference

Conference2021 International Conference on Visual Communications and Image Processing (VCIP)
Abbreviated titleVCIP 2-21
Period5/12/218/12/21

Keywords

  • deep learning
  • video coding
  • image coding
  • codecs
  • visual communication
  • forensics
  • transform coding

Fingerprint

Dive into the research topics of 'Security and forensics exploration of learning-based image coding'. Together they form a unique fingerprint.

Cite this