Year-end Sale % OFF 
Abstract
Generative adversarial network (GAN) has been regarded as a promising solution to many machine learning problems, and it comprises of a generator and discriminator, determining patterns and anomalies in the input data. However, GANs have several common failure modes. Typically, a mode collapse occurs when a GAN fails to fit the set optimizations and leads to several instabilities in the generative model, diminishing the capability to generate new content regardless of the dataset. In this paper, we study conditional limiter solutions for mode collapse for the Intrusion Detection System (IDS) Control Flow GAN (ICF-GAN) model. Specifically, the ICF-GAN’s mode collapse instances are limited by a mini-batch method that significantly improves the model accuracy. Performance evaluation is conducted using numerical results obtained from experiments.
Highlights
Generative adversarial networks (GAN) are unsupervised learning models, which comprise of a generator and discriminator, determining patterns and anomalies in the input data [1]
The problem of mode collapse can be explained in terms of gradient exploding where there is imbalance or inconsistency exists between generator and discriminator
We proposed to enhance the GAN-enabled ingestion process for PCAPbased malware detection (i.e., Intrusion Detection System) similar to the proactive analysis Causal Analysis based on System Theory (CAST) model [4,5]
Summary
Generative adversarial networks (GAN) are unsupervised learning models, which comprise of a generator and discriminator, determining patterns and anomalies in the input data [1]. Alternative methods address mode collapse issues with varieties of proposed GAN architectures, including Wasserstein GAN (WGAN) [11], unrolled GAN [12,13], AdaGAN [14], VEEGAN [15], zero-entered gradient penalty on training examples (GAN0GP) [16], zero-entered gradient penalty on interpolated samples (GAN-0GP) [17] and nudged-Adam (NuGAN) [18]. These architectures have been computed on different distributions of data as well as both synthetic and real datasets.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
