Oct 11, 2018 · In this study we propose MDGAN, a novel GAN architecture for improving anomaly detection through the generation of additional samples.

This study proposes MDGAN, a novel GAN architecture for improving anomaly detection through the generation of additional samples that can eventually be ...

Generative adversarial networks (GANs) have been used to generate additional training samples for classifiers, thus making them more accurate and robust.

Oct 11, 2018 · Our approach uses two discriminators: a dense network for determining whether the generated samples are of sufficient quality (i.e., valid) and ...

Yotam Intrator, Gilad Katz, Asaf Shabtai: MDGAN: Boosting Anomaly Detection Using Multi-Discriminator Generative Adversarial Networks.

Dive into the research topics of 'MDGAN: Boosting Anomaly Detection Using \\Multi-Discriminator Generative Adversarial Networks'. Together they form a unique ...

Firstly, we introduce intrusion detection system and anomaly detection. And then we do some research on machine learning techniques for anomaly detection by ...

MDGAN: Boosting Anomaly Detection Using \Multi-Discriminator Generative Adversarial Networks · no code implementations • 11 Oct 2018 • Yotam Intrator, Gilad ...

Generative adversarial networks (GANs) have been used to generate additional training samples for classifiers, thus making them more accurate and robust.

MDGAN: Boosting Anomaly Detection Using Multi-Discriminator Generative Adversarial Networks · Yotam IntratorGilad KatzA. Shabtai. Computer Science. ArXiv. 2018.