Real, Fake and Synthetic Faces - Does the Coin Have Three Sides?

Shahzeb Naeem, Ramzi Al-Sharawi, M. Riyyan Khan, Usman Tariq, Abhinav Dhall, Hasan Al Nashash

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the ever-growing power of generative artificial intelligence, deepfake and artificially generated (synthetic) media have continued to spread online, which creates various ethical and moral concerns regarding their usage. To tackle this, we thus present a novel exploration of the trends and patterns observed in real, deepfake and synthetic facial images. The proposed analysis is done in two parts: firstly, we incorporate eight deep learning models and analyze their performances in distinguishing between the three classes of images. Next, we look to further delve into the similarities and differences between these three sets of images by investigating their image properties both in the context of the entire image as well as in the context of specific regions within the image. ANOVA test was also performed and provided further clarity amongst the patterns associated between the images of the three classes. From our findings, we observe that the investigated deep-learning models found it easier to detect synthetic facial images, with the ViT Patch-16 model performing best on this task with a class-averaged sensitivity, specificity, precision, and accuracy of 97.37%, 98.69%, 97.48%, and 98.25%, respectively. This observation was supported by further analysis of various image properties. We saw noticeable differences across the three category of images. This analysis can help us build better algorithms for facial image generation, and also shows that synthetic, deepfake and real face images are indeed three different classes.

Original languageEnglish
Title of host publication2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)
PublisherInstitute of Electrical and Electronics Engineers
Number of pages10
ISBN (Electronic)9798350394948
DOIs
Publication statusPublished - 11 Jul 2024
Event18th IEEE International Conference on Automatic Face and Gesture Recognition - Istanbul, Turkey
Duration: 27 May 202431 May 2024
Conference number: 18th
https://fg2024.ieee-biometrics.org/

Publication series

NameIEEE 18th International Conference on Automatic Face and Gesture Recognition
Volume2024
ISSN (Electronic)2770-8330

Conference

Conference18th IEEE International Conference on Automatic Face and Gesture Recognition
Abbreviated titleFG 2024
Country/TerritoryTurkey
CityIstanbul
Period27/05/2431/05/24
OtherThe IEEE conference series on Automatic Face and Gesture Recognition is the premier international forum for research in image and video-based face, gesture, and body movement recognition. It is co-sponsored by IEEE Biometrics Council and IEEE Computer Society, and supported by Istanbul Technical University. Its broad scope includes advances in fundamental computer vision, pattern recognition, and computer graphics; machine learning techniques relevant to face, gesture, and body motion; interdisciplinary research on behavioral analysis; new algorithms and applications.
Internet address

Fingerprint

Dive into the research topics of 'Real, Fake and Synthetic Faces - Does the Coin Have Three Sides?'. Together they form a unique fingerprint.

Cite this