L Olagoke, S Vadhan, S Neel - arXiv preprint arXiv:2310.12063, 2023 - arxiv.org
Since their inception Generative Adversarial Networks (GANs) have been popular generative models across images, audio, video, and tabular data. In this paper we study …
Generative Adversarial Networks (GANs) have made releasing of synthetic images a viable approach to share data without releasing the original dataset. It has been shown that such …
H Sun, T Zhu, J Li, S Ji, W Zhou - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With breakthroughs in high-resolution image generation, applications for disentangled generative adversarial networks (GANs) have attracted much attention. At the same time, the …
Generative Adversarial Networks (GANs) have made releasing of synthetic images a viable approach to share data without releasing the original dataset. It has been shown that such …
H Hu, J Pang - Proceedings of the 2021 ACM SIGSAC Conference on …, 2021 - dl.acm.org
Generative adversarial networks (GANs) have made unprecedented performance in image synthesis and play a key role in various downstream applications of computer vision …
H Hu, J Pang - Proceedings of the 37th Annual Computer Security …, 2021 - dl.acm.org
Model extraction attacks aim to duplicate a machine learning model through query access to a target model. Early studies mainly focus on discriminative models. Despite the success …
M Joslin, S Hao - 2020 IEEE Security and Privacy Workshops …, 2020 - ieeexplore.ieee.org
The quality of GAN-generated fake images has improved significantly, and recent GAN approaches, such as StyleGAN, achieve near indistinguishability from real images for the …
To detect GAN generated images, conventional supervised machine learning algorithms require collecting a large number of real images as well as fake images generated by the …
A Alshantti, A Rasheed, F Westad - arXiv preprint arXiv:2404.00696, 2024 - arxiv.org
Generative models are subject to overfitting and thus may potentially leak sensitive information from the training data. In this work. we investigate the privacy risks that can …