Could Human Gaze Augment Detectors of Synthetic Images?

Nikolaos Fotopoulos, Clara Riedmiller, Efe Bozkir, Panagiotis Tsinganos, Dimitris Ampeliotis, Gjergji Kasneci, Enkelejda Kasneci, Athanassios Skodras

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

Abstract

Recent advances in generative adversarial networks (GANs) allow for the synthesis of extremely photo-realistic face images, deceiving even the most experienced observers, let alone the unsuspecting internet user. Due to this, there has been a considerable effort by the image forensics community to design appropriate tools for the detection of these images. This paper first implements one such detection technique based on spatial and cross-band co-occurrence matrices and convolutional neural networks (CNNs), and then attempts to improve it by introducing additional information obtained from the human gaze. We show that in cases where human observers correctly decide whether an image is real or fake, eye movement information in combination with spatial and cross-band co-occurrence matrices derived from observation regions can be informative towards the task of detecting fake images. However, only a limited increase in the detection accuracy is achieved.

OriginalspracheEnglisch
Titel2023 24th International Conference on Digital Signal Processing, DSP 2023
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
ISBN (elektronisch)9798350339598
DOIs
PublikationsstatusVeröffentlicht - 2023
Veranstaltung24th International Conference on Digital Signal Processing, DSP 2023 - Rhodes, Griechenland
Dauer: 11 Juni 202313 Juni 2023

Publikationsreihe

NameInternational Conference on Digital Signal Processing, DSP
Band2023-June

Konferenz

Konferenz24th International Conference on Digital Signal Processing, DSP 2023
Land/GebietGriechenland
OrtRhodes
Zeitraum11/06/2313/06/23

Fingerprint

Untersuchen Sie die Forschungsthemen von „Could Human Gaze Augment Detectors of Synthetic Images?“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren