Australian Journal of Wireless Technologies, Mobility and Security

AI-Enabled Security Protocols for Safeguarding Wireless Communications and IOT Devices

Pritam Gajkumar Shah — 2025-02-11

The rapid growth of Internet of Things (IoT) devices and wireless communication technologies has introduced significant security challenges. Traditional security protocols are often inadequate to address the dynamic and complex nature of modern cyber threats. This paper explores the integration of Artificial Intelligence (AI) into security protocols to enhance the protection of wireless communications and IoT devices. We discuss the limitations of conventional methods, the role of AI in detecting and mitigating threats, and the development of AI-enabled security frameworks. Case studies and experimental results demonstrate the effectiveness of AI-driven approaches in safeguarding IoT ecosystems. The paper concludes with recommendations for future research and implementation strategies.

Innovative AI-Based Protocol to Mitigate DDoS Attacks on City Infrastructure

Pritam Gajkumar Shah — 2025-02-11

Distributed Denial of Service (DDoS) attacks pose a significant threat to city infrastructure, disrupting essential services such as critical infrastrcture, healthcare, and utilities. Traditional mitigation techniques often fail to address the scale and sophistication of modern DDoS attacks. This paper proposes an innovative AI-driven protocol designed to detect, analyze, and mitigate DDoS attacks in real-time. Leveraging machine learning (ML) and deep learning (DL) algorithms, the protocol adapts to evolving attack patterns and ensures the resilience of smart city infrastructure. Experimental results demonstrate the protocol's effectiveness in reducing attack impact and maintaining service availability. The paper concludes with recommendations for implementation and future research directions.

AI for Penetration Testing: Enhancing Cybersecurity Through Intelligent Automation

Pritam Gajkumar Shah — 2025-02-12

Penetration testing is a critical component of cybersecurity, aimed at identifying vulnerabilities in systems before malicious actors can exploit them. Traditional penetration testing methods are often time-consuming, labor-intensive, and limited by human expertise. This paper explores the application of Artificial Intelligence (AI) in penetration testing, highlighting its potential to automate vulnerability detection, optimize attack simulations, and improve overall efficiency. Through case studies and examples, we demonstrate how AI-driven tools can enhance the accuracy and scalability of penetration testing. The paper concludes with a discussion of challenges and future directions for AI in this domain.

A case study of implementing COBIT 5 framework for E commerce web site

Sujan Poudel — 2025-04-08

This paper presents a comprehensive case study on the application of the COBIT 5 framework to an e-commerce website. The implementation utilizes a Linux-based web hosting environment with unmetered bandwidth , SSD storage and SSL certificate so that users information will reach server via HTTPS protocol. . For demonstration purposes, the AbanteCart script has been employed. The study systematically addresses key challenges related to the confidentiality, integrity, and availability of online transactions, along with the protection of user data privacy. It is important to note that this work does not introduce any novel innovations; rather, it is based entirely on currently available technologies and best practices.

How AI is Automating Data Cleaning and Feature Engineering in Data Science Pipelines

manish chaudhary — 2025-10-21

Data preparation—including cleaning and feature engineering—has long been one of the most time-consuming yet critical stages in the data science workflow. Traditionally done manually, it demands a large share of time and is prone to human error. As datasets grow in volume and complexity, the need for automated, intelligent solutions becomes increasingly urgent. This article explores how Artificial Intelligence (AI) is revolutionizing this space. From anomaly detection and semantic matching to AutoML-driven feature generation and AI-guided selection techniques, AI is accelerating and enhancing the quality of data preparation. Through practical tools, case studies, and forward-looking trends, we show how AI not only saves time but improves accuracy, scalability, and reproducibility, while freeing human analysts to focus on higher-value tasks.