Access our collection of peer-reviewed research papers and academic publications
Generative Adversarial Nets
GANResearch Article
Authors: Author Clustor
This paper introduces Generative Adversarial Networks (GANs), where two neural networks compete: a generator creates synthetic data while a discriminator evaluates it. The framework enables realistic data generation including images and videos.
This paper explores how attackers can infer sensitive information from trained machine learning classifiers. By building a meta-classifier, researchers demonstrate how models may leak hidden details about training data and system design.