Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Survey on the Application of Generative Adversarial Networks in Cybersecurity: Prospective, Direction and Open Research Scopes

Md Mashrur Arifin, Md Shoaib Ahmed, Tanmai Kumar Ghosh, Ikteder Akhand Udoy, Jun Zhuang, Jyh-haw Yeh

TL;DR

This survey studies the significance of the deep learning model, precisely on GANs, in strengthening cybersecurity defenses and explores the various works completed in GANs to examine how GANs can be influential tools to strengthen cybersecurity defenses in these domains.

Abstract

With the proliferation of Artificial Intelligence, there has been a massive increase in the amount of data required to be accumulated and disseminated digitally. As the data are available online in digital landscapes with complex and sophisticated infrastructures, it is crucial to implement various defense mechanisms based on cybersecurity. Generative Adversarial Networks (GANs), which are deep learning models, have emerged as powerful solutions for addressing the constantly changing security issues. This survey studies the significance of the deep learning model, precisely on GANs, in strengthening cybersecurity defenses. Our survey aims to explore the various works completed in GANs, such as Intrusion Detection Systems (IDS), Mobile and Network Trespass, BotNet Detection, and Malware Detection. The focus is to examine how GANs can be influential tools to strengthen cybersecurity defenses in these domains. Further, the paper discusses the challenges and constraints of using GANs in these areas and suggests future research directions. Overall, the paper highlights the potential of GANs in enhancing cybersecurity measures and addresses the need for further exploration in this field.

A Survey on the Application of Generative Adversarial Networks in Cybersecurity: Prospective, Direction and Open Research Scopes

TL;DR

This survey studies the significance of the deep learning model, precisely on GANs, in strengthening cybersecurity defenses and explores the various works completed in GANs to examine how GANs can be influential tools to strengthen cybersecurity defenses in these domains.

Abstract

With the proliferation of Artificial Intelligence, there has been a massive increase in the amount of data required to be accumulated and disseminated digitally. As the data are available online in digital landscapes with complex and sophisticated infrastructures, it is crucial to implement various defense mechanisms based on cybersecurity. Generative Adversarial Networks (GANs), which are deep learning models, have emerged as powerful solutions for addressing the constantly changing security issues. This survey studies the significance of the deep learning model, precisely on GANs, in strengthening cybersecurity defenses. Our survey aims to explore the various works completed in GANs, such as Intrusion Detection Systems (IDS), Mobile and Network Trespass, BotNet Detection, and Malware Detection. The focus is to examine how GANs can be influential tools to strengthen cybersecurity defenses in these domains. Further, the paper discusses the challenges and constraints of using GANs in these areas and suggests future research directions. Overall, the paper highlights the potential of GANs in enhancing cybersecurity measures and addresses the need for further exploration in this field.
Paper Structure (62 sections, 10 equations, 5 figures, 10 tables)

This paper contains 62 sections, 10 equations, 5 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Intrusion Detection System
  4. Malware Detection
  5. Anomaly Detection
  6. Miscellaneous Cyber Threats
  7. Malicious Domain Detection
  8. Jamming Attack Detection
  9. AI-based Cyber Attack in Industry 4.0
  10. Fundamentals of Generative Adversarial Networks (GANs)
  11. GANs Defination
  12. GAN Variation
  13. Vanilla and Conditional GAN
  14. Wasserstein GAN (WGAN)
  15. Conditional Wasserstein GAN
  16. ...and 47 more sections

Figures (5)

  • Figure 1: A comprehensive overview of the state-of-the-art research on generative adversarial networks (GANs) and their applications in cybersecurity into nine sections. Each section covers a different aspect of the topic, such as the fundamentals of GANs, the cybersecurity challenges they pose and solve, the use cases and applications they enable, the security analysis they require, and the future directions they suggest. The diagram shows the survey's hierarchical structure, the sections' logical flow, and each subsection's main points.
  • Figure 2: This diagram illustrates the fundamental design of a Generative Adversarial Network (GAN). The two primary components of the GAN structure are the Generator and the Discriminator. The Generator creates fictitious data, and the Discriminator verifies the authenticity of the samples it creates. The Generator and Discriminator keep getting better at what they do through a process of constant adversarial training. This makes the data they produce more realistic.
  • Figure 3: Adversarial attack method based on GAN (AAM-GAN) AS3_zhang2020brute
  • Figure 4: This taxonomy portrays the distribution of diverse GANs deployed in various cybersecurity domains.
  • Figure 5: The proposed framework for MDGAN mazaed2022multifaceted