{"id":{"repo_id":"alabama","oai_identifier":"oai:ir.ua.edu:123456789/17603"},"canonical_url":"https://search.dev.ndltd.org/etd/alabama/oai:ir.ua.edu:123456789/17603","repository":{"repo_id":"alabama","name":"University of Alabama","base_url":"https://ir-api.ua.edu/oai/request"},"display":{"title":"The Effectiveness of Firefly and Greywolf Algorithm Techniques in the Detection of Phishing Intrusion within Cloud-Based Systems","abstract":"Phishing attacks continue to pose significant threats to cyber security, particularly in cloud-based systems that are heavily reliant on user authentication and remote access mechanisms. These attacks exploit system vulnerabilities to deceive users and gain unauthorized access to sensitive data, causing major financial and reputational damage. Despite the availability of several machine learning based phishing detection models, the increasing sophistication of phishing tactics demands more intelligent and adaptive detection mechanisms. This dissertation explores the use of Nature Inspired Algorithms (NIAs), specifically the Firefly Optimization Algorithm (FOA) and Grey-wolf Optimization (GWO),to optimize machine learning models for phishing detection in cloud-based environments. The data used for this study was sourced from the Mendeley Data Repository. Originally collected and compiled by Hannousse and Yahiouche in 2020, the dataset comprises 11,430 URL records, equally divided between benign and malicious links. It includes 88 extracted features relevant to phishing behavior, excluding the target variable 'URL class', which indicates whether a link is phishing (1) or benign (0). The research investigates the enhancement of traditional machine learning classifiers, Random Forest (RF) and Gradient Boosting (GB), through the integration of FOA and GWO for feature selection and hyperparameter tuning. The experimental results indicate that the FOA-optimized RF model achieved a classification accuracy of 98.02% and a precision of 97.89%, while the GWO-enhanced GB model reached an accuracy of 97.5% and demonstrated improved recall and reduced false positives. These performance gains validate the hypothesis that Nature-Inspired Algorithms can significantly improve the detection capabilities of phishing classifiers in cloud-based infrastructures. This dissertation contributes to the evolving field of cyber threat mitigation by demonstrating the practical benefits of incorporating bio-inspired computational techniques into phishing detection systems. The proposed hybrid models not only improve detection accuracy but also enhance the robustness and adaptability of cloud security frameworks. The findings emphasize the importance of integrating intelligent optimization strategies into cyber security systems and open new avenues for future research, including real-time phishing detection, integration with deep learning models, and deployment in distributed cloud environments.","abstract_html":"Phishing attacks continue to pose significant threats to cyber security, particularly in cloud-based systems that are heavily reliant on user authentication and remote access mechanisms. These attacks exploit system vulnerabilities to deceive users and gain unauthorized access to sensitive data, causing major financial and reputational damage. Despite the availability of several machine learning based phishing detection models, the increasing sophistication of phishing tactics demands more intelligent and adaptive detection mechanisms. This dissertation explores the use of Nature Inspired Algorithms (NIAs), specifically the Firefly Optimization Algorithm (FOA) and Grey-wolf Optimization (GWO),to optimize machine learning models for phishing detection in cloud-based environments. The data used for this study was sourced from the Mendeley Data Repository. Originally collected and compiled by Hannousse and Yahiouche in 2020, the dataset comprises 11,430 URL records, equally divided between benign and malicious links. It includes 88 extracted features relevant to phishing behavior, excluding the target variable 'URL class', which indicates whether a link is phishing (1) or benign (0). The research investigates the enhancement of traditional machine learning classifiers, Random Forest (RF) and Gradient Boosting (GB), through the integration of FOA and GWO for feature selection and hyperparameter tuning. The experimental results indicate that the FOA-optimized RF model achieved a classification accuracy of 98.02% and a precision of 97.89%, while the GWO-enhanced GB model reached an accuracy of 97.5% and demonstrated improved recall and reduced false positives. These performance gains validate the hypothesis that Nature-Inspired Algorithms can significantly improve the detection capabilities of phishing classifiers in cloud-based infrastructures. This dissertation contributes to the evolving field of cyber threat mitigation by demonstrating the practical benefits of incorporating bio-inspired computational techniques into phishing detection systems. The proposed hybrid models not only improve detection accuracy but also enhance the robustness and adaptability of cloud security frameworks. The findings emphasize the importance of integrating intelligent optimization strategies into cyber security systems and open new avenues for future research, including real-time phishing detection, integration with deep learning models, and deployment in distributed cloud environments.","abstract_has_math":false,"creators":["Ovabor, Kelvin Osahon"],"institution":"University of Alabama Libraries","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Carver, Jeffery","Pu, Lina","Rahman, Md Rayhanur","Jeong, Nathan"],"advisors":["Atkison, Travis"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-27T18:44:22Z","subjects":[],"languages":["en_US","English"],"rights":["All rights reserved by the author unless otherwise indicated."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["1198945"],"render_values":[{"text":"1198945","href":null,"code":true}]}]},"links":{"outbound_url":"https://ir.ua.edu/handle/123456789/17603","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Carver, Jeffery","Pu, Lina","Rahman, Md Rayhanur","Jeong, Nathan"]},{"key":"dc:contributor.advisor","label":"Advisor","values":["Atkison, Travis"]},{"key":"dc:creator","label":"Author","values":["Ovabor, Kelvin Osahon"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-02-09T22:56:31Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-02-09T22:56:31Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:publisher","label":"Institution","values":["University of Alabama Libraries"]},{"key":"dc:type","label":"Dc Type","values":["thesis","text"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["All rights reserved by the author unless otherwise indicated."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["1198945"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://ir.ua.edu/handle/123456789/17603"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Electronic Thesis or Dissertation"]},{"key":"dc:description.abstract","label":"Abstract","values":["Phishing attacks continue to pose significant threats to cyber security, particularly in cloud-based systems that are heavily reliant on user authentication and remote access mechanisms. These attacks exploit system vulnerabilities to deceive users and gain unauthorized access to sensitive data, causing major financial and reputational damage. Despite the availability of several machine learning based phishing detection models, the increasing sophistication of phishing tactics demands more intelligent and adaptive detection mechanisms. This dissertation explores the use of Nature Inspired Algorithms (NIAs), specifically the Firefly Optimization Algorithm (FOA) and Grey-wolf Optimization (GWO),to optimize machine learning models for phishing detection in cloud-based environments. The data used for this study was sourced from the Mendeley Data Repository. Originally collected and compiled by Hannousse and Yahiouche in 2020, the dataset comprises 11,430 URL records, equally divided between benign and malicious links. It includes 88 extracted features relevant to phishing behavior, excluding the target variable 'URL class', which indicates whether a link is phishing (1) or benign (0). The research investigates the enhancement of traditional machine learning classifiers, Random Forest (RF) and Gradient Boosting (GB), through the integration of FOA and GWO for feature selection and hyperparameter tuning. The experimental results indicate that the FOA-optimized RF model achieved a classification accuracy of 98.02% and a precision of 97.89%, while the GWO-enhanced GB model reached an accuracy of 97.5% and demonstrated improved recall and reduced false positives. These performance gains validate the hypothesis that Nature-Inspired Algorithms can significantly improve the detection capabilities of phishing classifiers in cloud-based infrastructures. This dissertation contributes to the evolving field of cyber threat mitigation by demonstrating the practical benefits of incorporating bio-inspired computational techniques into phishing detection systems. The proposed hybrid models not only improve detection accuracy but also enhance the robustness and adaptability of cloud security frameworks. The findings emphasize the importance of integrating intelligent optimization strategies into cyber security systems and open new avenues for future research, including real-time phishing detection, integration with deep learning models, and deployment in distributed cloud environments."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["electronic"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["The Effectiveness of Firefly and Greywolf Algorithm Techniques in the Detection of Phishing Intrusion within Cloud-Based Systems"]}]}],"canonical_facts":{"dc:contributor":["Carver, Jeffery","Pu, Lina","Rahman, Md Rayhanur","Jeong, Nathan"],"dc:contributor.advisor":["Atkison, Travis"],"dc:creator":["Ovabor, Kelvin Osahon"],"dc:date.accessioned":["2026-02-09T22:56:31Z"],"dc:date.available":["2026-02-09T22:56:31Z"],"dc:date.issued":["2025"],"dc:description":["Electronic Thesis or Dissertation"],"dc:description.abstract":["Phishing attacks continue to pose significant threats to cyber security, particularly in cloud-based systems that are heavily reliant on user authentication and remote access mechanisms. These attacks exploit system vulnerabilities to deceive users and gain unauthorized access to sensitive data, causing major financial and reputational damage. Despite the availability of several machine learning based phishing detection models, the increasing sophistication of phishing tactics demands more intelligent and adaptive detection mechanisms. This dissertation explores the use of Nature Inspired Algorithms (NIAs), specifically the Firefly Optimization Algorithm (FOA) and Grey-wolf Optimization (GWO),to optimize machine learning models for phishing detection in cloud-based environments. The data used for this study was sourced from the Mendeley Data Repository. Originally collected and compiled by Hannousse and Yahiouche in 2020, the dataset comprises 11,430 URL records, equally divided between benign and malicious links. It includes 88 extracted features relevant to phishing behavior, excluding the target variable 'URL class', which indicates whether a link is phishing (1) or benign (0). The research investigates the enhancement of traditional machine learning classifiers, Random Forest (RF) and Gradient Boosting (GB), through the integration of FOA and GWO for feature selection and hyperparameter tuning. The experimental results indicate that the FOA-optimized RF model achieved a classification accuracy of 98.02% and a precision of 97.89%, while the GWO-enhanced GB model reached an accuracy of 97.5% and demonstrated improved recall and reduced false positives. These performance gains validate the hypothesis that Nature-Inspired Algorithms can significantly improve the detection capabilities of phishing classifiers in cloud-based infrastructures. This dissertation contributes to the evolving field of cyber threat mitigation by demonstrating the practical benefits of incorporating bio-inspired computational techniques into phishing detection systems. The proposed hybrid models not only improve detection accuracy but also enhance the robustness and adaptability of cloud security frameworks. The findings emphasize the importance of integrating intelligent optimization strategies into cyber security systems and open new avenues for future research, including real-time phishing detection, integration with deep learning models, and deployment in distributed cloud environments."],"dc:format.medium":["electronic"],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["1198945"],"dc:identifier.uri":["https://ir.ua.edu/handle/123456789/17603"],"dc:language":["English"],"dc:language.iso":["en_US"],"dc:publisher":["University of Alabama Libraries"],"dc:rights":["All rights reserved by the author unless otherwise indicated."],"dc:title":["The Effectiveness of Firefly and Greywolf Algorithm Techniques in the Detection of Phishing Intrusion within Cloud-Based Systems"],"dc:type":["thesis","text"]},"updated_at":"2026-07-27T18:44:22Z"}