Back to search

Virginia Commonwealth University

Explore Security and Machine Learning Applications in Next Generation Wireless Networks

Abstract

dc:description.abstract

Next-generation (NextG) or Beyond-Fifth-Generation (B5G) wireless networks have become a prominent focus in academic and industry circles. This is driven by the increasing demand for cutting-edge applications such as mobile health, self-driving cars, the metaverse, digital twins, virtual reality, and more. These diverse applications typically require high communication network performance, including spectrum utilization, data speed, and latency. New technologies are emerging to meet the communication requirements of various applications. Intelligent Reflecting Surface (IRS) and Artificial Intelligence (AI) are two representatives that have been demonstrated as promising and powerful technologies in NextG communications. While new technologies significantly enhance communication performance, they also introduce new security concerns. Therefore, security remains a top priority within the communication community. This dissertation studies innovative solutions for the security in NextG networks. Specifically, we will investigate the security applications of IRS and machine learning-based solutions to enhance security using wireless signal denoising and signal modulation recognition methods. Also, we will explore defending AI-powered communication systems against adversarial attacks. IRS can be utilized to flexibly re-configure the fundamental communication environment to realize low-cost, energy-saving, and low-interference wireless communications. However, one concern of the IRS is that malicious users may manipulate it to their advantage, which presents significant security issues. We will propose security scenarios of IRS communication systems and investigate how the IRS affects the Signal-to-Noise Ratio (SNR) with different experimental settings. Furthermore, the SNR plays a critical role in wireless security. SNR is constantly degraded during transmission in a practical communication environment due to interference from malicious attackers or surrounding noise. To address the problems, we will develop a Generative Adversarial Networks (GAN)-based signal denoising method to improve signal quality. Moreover, active malicious physical layer attacks such as spoofing and jamming can disrupt communications and bring unpredictable security risks. Automatic modulation Recognition (AMR), which identifies the modulation types of active attack signals, plays a crucial role in the physical-layer security of wireless communication. A new AMR method based on parallel neural networks will be proposed. In addition, while AI technologies have recently been integrated into NextG networks, the security threats and mitigation methods for AI-powered communication systems in NextG networks have not been thoroughly investigated. Therefore, we will explore the performance of AI-powered communication systems under machine learning adversarial attacks. The main objectives of this dissertation on AI-driven innovations to security in NextG networks are summarized as follows. We first introduce recent works on using IRS in wireless communications and present basic security scenarios from constructive and adversarial perspectives. Second, a GAN-based wireless signal-denoising method will be developed and compared with traditional algorithms. Third, a deep learning-based AMR method will be proposed and tested on various signal modulation schemes. Last, we investigate the vulnerability of AI-driven NextG communication systems under adversarial attacks and propose the defensive distillation mitigation method to improve its robustness.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
Dissertation
Discipline thesis:degree_discipline
Electrical & Computer Engineering

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Tang, Haolin
  • https://orcid.org/0000-0002-5115-999X
Contributors dc:contributor
  • Yanxiao Zhao

Subjects

dc:subject × 9

Rights

dc:rights
Statement dc:rights
  • © The Author

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Virginia Commonwealth University
Base URL
scholarscompass.vcu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Tang, Haolin; https://orcid.org/0000-0002-5115-999X. Explore Security and Machine Learning Applications in Next Generation Wireless Networks. Dissertation thesis, https://doi.org/10.25772/JVC4-KF82