Safe Scanner: Technical Report

Safi, Nedah Jan (2024) Safe Scanner: Technical Report. Undergraduate thesis, Dublin, National College of Ireland.

Preview

PDF (Bachelor of Science) Download (3MB) | Preview

Abstract

The purpose of creating Safe Scanner a web application is the is to enhance user security by ensuring that scanned QR codes lead to legitimate and safe URLs. Detecting malicious URLs is crucial for network and cybersecurity. Malicious URLs pose a significant threat, sharing unsolicited content like spam, phishing, and drive-by downloads. They lure unsuspecting users into scams, leading to monetary loss, theft of private information, and malware installation. (arxiv, 2019). For detecting malicious URLs blacklists have been the standard method for detecting harmful URLs, but they are not always accurate and fail to identify newly created malicious URLs. In recent years, machine learning approaches have attracted attention as an approach of improving the reliability of malicious URL detectors. Detecting malicious URLs using machine learning techniques. Machine learning techniques have been increasingly applied to solve the problems relating to information security and cybersecurity. Malicious URL (Uniform Resource Locator) detection is one of these (Vanhoenshoven et al. 2016). In this project, I've applied the random forest method to develop a machine learning model incorporating lexical features, host-based features, and content-based features. The model has an accuracy of 94.7%. The Safe Scanner web application operates in real-time, capturing video feed for QR code detection and processing. The code employs a systematic approach, checking for URL validity, legitimacy, and potential threats. The application is develop using python, JavaScript, HTML, CSS, Flask framework and VS Code. The report highlights the code implementation, emphasizing the integration steps. Users are provided with informative outputs regarding the safety and legitimacy of the detected QR code's URL. The system is flexible, allowing for future enhancements such as additional threat checks and improved user interfaces for a more intuitive experience.

Item Type:	Thesis (Undergraduate)
Supervisors:	Name Email Maycock, Keith UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Bachelor of Science (Honours) in Computing
Depositing User:	Ciara O'Brien
Date Deposited:	27 May 2025 13:24
Last Modified:	27 May 2025 13:24
URI:	https://norma.ncirl.ie/id/eprint/7671

Actions (login required)

View Item