Printing and scanning investigation for image counter forensics

Hailey James, Otkrist Gupta, Dan Raviv

Research output: Contribution to journalArticlepeer-review

Abstract

Examining the authenticity of images has become increasingly important as manipulation tools become more accessible and advanced. Recent work has shown that while CNN-based image manipulation detectors can successfully identify manipulations, they are also vulnerable to adversarial attacks, ranging from simple double JPEG compression to advanced pixel-based perturbation. In this paper we explore another method of highly plausible attack: printing and scanning. We demonstrate the vulnerability of two state-of-the-art models to this type of attack. We also propose a new machine learning model that performs comparably to these state-of-the-art models when trained and validated on printed and scanned images. Of the three models, our proposed model outperforms the others when trained and validated on images from a single printer. To facilitate this exploration, we create a data set of over 6000 printed and scanned image blocks. Further analysis suggests that variation between images produced from different printers is significant, large enough that good validation accuracy on images from one printer does not imply similar validation accuracy on identical images from a different printer.

Original languageEnglish
Article number2
JournalEurasip Journal on Image and Video Processing
Volume2022
Issue number1
DOIs
StatePublished - Dec 2022
Externally publishedYes

Keywords

  • Adversarial attack
  • Computer vision
  • Image forensics

Fingerprint

Dive into the research topics of 'Printing and scanning investigation for image counter forensics'. Together they form a unique fingerprint.

Cite this