Iranian Society of Cryptology The ISC International Journal of Information Security 2008-2045 17 2 2025 07 01 A Fine-Grained Hybrid Inversion-Based Membership Inference Attack Against GANs 189 198 216445 10.22042/isecure.2025.216445 EN Maryam Azadmanesh Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran Journal Article 2025 03 01 Generative Adversarial Networks (GANs) are commonly used in various applications. Different membership inference attacks have been carried out against GANs. However, the accuracy of these attacks decreases with a large number of training samples, and there have been no attacks conducted against privacy-preserving GAN models with dependent or independent datasets. Therefore, this paper proposes a fine-grained inversion-based attack. In this proposed attack, fine-grained reconstruction error is utilized to infer the membership or non-membership of given samples. To calculate the<br />reconstruction error, an inversion-based encoder is trained, and the latent code obtained from the encoder is refined using a Genetic Algorithm. The membership status of the candidate target sample is determined using the reconstruction error of the segmentations of the target sample. The proposed attack can be executed by accessing the generator network in both black and white-box settings. The accuracy of the proposed attack is compared with other relevant studies, demonstrating its superior performance. Furthermore, the results indicate that privacy-preserving mechanisms do not ensure that dependent data does not disclose information about individual samples. https://www.isecure-journal.com/article_216445_e3b68d7b0aa352c64c822a3b311095c0.pdf