Logo image
Back
Convergence Behaviors and Variabilities of Loss Functions in Quantum GANs and GANs
Conference proceeding   Peer reviewed

Convergence Behaviors and Variabilities of Loss Functions in Quantum GANs and GANs

Md Abdur Rahman, Alfredo Cuzzocrea and Hossain Shahriar
Proceedings - International Conference on Distributed Computing Systems Workshops, pp.38-43
International Conference on Distributed Computing Systems Workshops (ICDCSW), 45th (Glasgow, Scotland, UK, 07/21/2025–07/23/2025)
12/2025
DOI: https://doi.org/10.1109/ICDCSW63273.2025.00013
Web of Science ID: WOS:001669747800007

Metrics

1 Record Views

Abstract

The rapid advancement of Quantum Machine Learning (QML) has introduced new possibilities and challenges in the field of cybersecurity. Generative Adversarial Networks (GANs) have been used as promising tools in Machine Learning (ML) and QML for generating realistic synthetic data from existing (real) dataset which aids in the analysis, detection, and protection against adversarial attacks. In fact, Quantum Generative Adversarial Networks (QGANs) has great ability for numerical data as well as image data generation which have high-dimensional features using the property of quantum superposition. However, effectively loading datasets onto quantum computers encounters significant obstacles due to losses and inherent noise which affects performance. In this work, we study the impact of various losses during training of QGANs as well as GANs for various state-of-the-art cybersecurity datasets. This paper presents a comparative analysis of the stability of loss functions for real datasets as well as GANs generated synthetic dataset. Therefore, we conclude that QGANs demonstrate superior stability and maintain consistently lower generator loss values than traditional machine learning approaches like GANs. Consequently, experimental results indicate that the stability of the loss function is more pronounced for QGANs than GANs.

Details

Logo image