GAN-ISI: Generative Adversarial Networks Image Source Identification Using Texture Analysis
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Standard
GAN-ISI : Generative Adversarial Networks Image Source Identification Using Texture Analysis. / Ghazi, Mehdi Mehdipour; Ghazi, Mostafa Mehdipour.
I: CEUR Workshop Proceedings, Bind 3497, 2023, s. 1588-1595.Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - GAN-ISI
T2 - 24th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF-WN 2023
AU - Ghazi, Mehdi Mehdipour
AU - Ghazi, Mostafa Mehdipour
N1 - Publisher Copyright: © 2023 Copyright for this paper by its authors.
PY - 2023
Y1 - 2023
N2 - Generative adversarial networks (GANs) have emerged as powerful tools for generating realistic images in various domains, including healthcare and medicine. However, concerns surrounding the privacy and security of personal data have become prominent. This study investigates the presence of fingerprints in synthetic medical images generated by GANs, which may indicate traces of the real images used during training and raise concerns about the sharing and limitations imposed by sensitive medical data. To address this, we analyze the texture characteristics of real and synthetic images from the ImageCLEF2023 Medical GANs challenge datasets, utilizing a range of texture descriptors and analysis methods to identify discernible patterns within the synthetic image data and determine the source images employed for training. We calculate the cumulative distribution function (CDF) of texture feature maps and apply the Wasserstein distance to compare the CDFs of the query and generated images. A binary classifier is trained to predict the utilization of the query image in generating each GAN image. The obtained results demonstrate balanced performance across various evaluation metrics, with the model exhibiting good generalization to the challenge test set, achieving an accuracy of 0.54 and an F1-score above 0.5. Our findings provide valuable insights into the security and privacy considerations when generating and utilizing artificial medical images in real-life scenarios.
AB - Generative adversarial networks (GANs) have emerged as powerful tools for generating realistic images in various domains, including healthcare and medicine. However, concerns surrounding the privacy and security of personal data have become prominent. This study investigates the presence of fingerprints in synthetic medical images generated by GANs, which may indicate traces of the real images used during training and raise concerns about the sharing and limitations imposed by sensitive medical data. To address this, we analyze the texture characteristics of real and synthetic images from the ImageCLEF2023 Medical GANs challenge datasets, utilizing a range of texture descriptors and analysis methods to identify discernible patterns within the synthetic image data and determine the source images employed for training. We calculate the cumulative distribution function (CDF) of texture feature maps and apply the Wasserstein distance to compare the CDFs of the query and generated images. A binary classifier is trained to predict the utilization of the query image in generating each GAN image. The obtained results demonstrate balanced performance across various evaluation metrics, with the model exhibiting good generalization to the challenge test set, achieving an accuracy of 0.54 and an F1-score above 0.5. Our findings provide valuable insights into the security and privacy considerations when generating and utilizing artificial medical images in real-life scenarios.
KW - cumulative distribution function
KW - Generative adversarial networks
KW - source identification
KW - texture descriptors
KW - Wasserstein distance
M3 - Conference article
AN - SCOPUS:85175628270
VL - 3497
SP - 1588
EP - 1595
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
SN - 1613-0073
Y2 - 18 September 2023 through 21 September 2023
ER -
ID: 373547770