Evaluating Privacy on Synthetic Images Generated using GANs: Contributions of the VCMI Team to ImageCLEFmedical GANs 2023

• Type: Article in International Conference Proceedings Book
• Date: 2023

Authors

Montenegro, H (Author) Other; Neto, PC (Author) Other; Patrício, C (Author) Other; Torto, IR (Author) Other; Gonçalves, T (Author) Other; Luis F Teixeira (Author) FEUP

Conference proceedings International

Title: Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2023), Thessaloniki, Greece, September 18th to 21st, 2023.

Pages: 1596-1610

24th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF-WN 2023

Thessaloniki, 18 September 2023 through 21 September 2023

Indexing

Scopus - 1 Citation

Other information

Authenticus ID: P-00Z-CWP

Abstract (EN): This paper presents the main contributions of the VCMI Team to the ImageCLEFmedical GANs 2023 task. This task aims to evaluate whether synthetic medical images generated using Generative Adversarial Networks (GANs) contain identifiable characteristics of the training data. We propose various approaches to classify a set of real images as having been used or not used in the training of the model that generated a set of synthetic images. We use similarity-based approaches to classify the real images based on their similarity to the generated ones. We develop autoencoders to classify the images through outlier detection techniques. Finally, we develop patch-based methods that operate on patches extracted from real and generated images to measure their similarity. On the development dataset, we attained an F1-score of 0.846 and an accuracy of 0.850 using an autoencoder-based method. On the test dataset, a similarity-based approach achieved the best results, with an F1-score of 0.801 and an accuracy of 0.810. The empirical results support the hypothesis that medical data generated using deep generative models trained without privacy constraints threatens the privacy of patients in the training data. © 2023 Copyright for this paper by its authors.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 14