PhishGuard: Machine learning-powered phishing URL detection
Phishing is a major threat to internet security, targeting human vulnerabilities instead of software vulnerabilities. It involves directing users to malicious websites where their sensitive information can be stolen. Many researchers have worked on detecting phishing URLs, but their models have limi...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2023
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/41831/ http://umpir.ump.edu.my/id/eprint/41831/1/PhishGuard_Machine%20learning-powered%20phishing%20URL%20detection.pdf http://umpir.ump.edu.my/id/eprint/41831/2/PhishGuard_Machine%20learning-powered%20phishing%20URL%20detection_ABS.pdf |
| _version_ | 1848826444227018752 |
|---|---|
| author | Murad, Saydul Akbar Rahimi, Nick Abu Jafar, Md Muzahid |
| author_facet | Murad, Saydul Akbar Rahimi, Nick Abu Jafar, Md Muzahid |
| author_sort | Murad, Saydul Akbar |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Phishing is a major threat to internet security, targeting human vulnerabilities instead of software vulnerabilities. It involves directing users to malicious websites where their sensitive information can be stolen. Many researchers have worked on detecting phishing URLs, but their models have limitations such as low accuracy and high false positives. To address these issues, we propose a machine-learning model to detect phishing URLs. To detect these malicious URLs, we use a dataset of over 500K entries collected from the Kaggle website. The dataset is used to train five supervised machine-learning techniques, including K-Nearest Neighbors (KNN), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF). The aim is to improve the performance of the classifier by studying the features of phishing websites and selecting a better combination of them. To measure the performance, we considered three parameters: accuracy, precision, and recall. The LR technique yielded the best performance, demonstrating its efficacy in detecting phishing URLs. |
| first_indexed | 2025-11-15T03:44:55Z |
| format | Conference or Workshop Item |
| id | ump-41831 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-15T03:44:55Z |
| publishDate | 2023 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-418312024-08-30T00:10:29Z http://umpir.ump.edu.my/id/eprint/41831/ PhishGuard: Machine learning-powered phishing URL detection Murad, Saydul Akbar Rahimi, Nick Abu Jafar, Md Muzahid QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) Phishing is a major threat to internet security, targeting human vulnerabilities instead of software vulnerabilities. It involves directing users to malicious websites where their sensitive information can be stolen. Many researchers have worked on detecting phishing URLs, but their models have limitations such as low accuracy and high false positives. To address these issues, we propose a machine-learning model to detect phishing URLs. To detect these malicious URLs, we use a dataset of over 500K entries collected from the Kaggle website. The dataset is used to train five supervised machine-learning techniques, including K-Nearest Neighbors (KNN), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF). The aim is to improve the performance of the classifier by studying the features of phishing websites and selecting a better combination of them. To measure the performance, we considered three parameters: accuracy, precision, and recall. The LR technique yielded the best performance, demonstrating its efficacy in detecting phishing URLs. Institute of Electrical and Electronics Engineers Inc. 2023 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/41831/1/PhishGuard_Machine%20learning-powered%20phishing%20URL%20detection.pdf pdf en http://umpir.ump.edu.my/id/eprint/41831/2/PhishGuard_Machine%20learning-powered%20phishing%20URL%20detection_ABS.pdf Murad, Saydul Akbar and Rahimi, Nick and Abu Jafar, Md Muzahid (2023) PhishGuard: Machine learning-powered phishing URL detection. In: Proceedings - 2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023. 2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023 , 24 - 27 July 2023 , Las Vegas. pp. 2279-2284. (198742). ISBN 979-835032759-5 (Published) https://doi.org/10.1109/CSCE60160.2023.00371 |
| spellingShingle | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) Murad, Saydul Akbar Rahimi, Nick Abu Jafar, Md Muzahid PhishGuard: Machine learning-powered phishing URL detection |
| title | PhishGuard: Machine learning-powered phishing URL detection |
| title_full | PhishGuard: Machine learning-powered phishing URL detection |
| title_fullStr | PhishGuard: Machine learning-powered phishing URL detection |
| title_full_unstemmed | PhishGuard: Machine learning-powered phishing URL detection |
| title_short | PhishGuard: Machine learning-powered phishing URL detection |
| title_sort | phishguard: machine learning-powered phishing url detection |
| topic | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) |
| url | http://umpir.ump.edu.my/id/eprint/41831/ http://umpir.ump.edu.my/id/eprint/41831/ http://umpir.ump.edu.my/id/eprint/41831/1/PhishGuard_Machine%20learning-powered%20phishing%20URL%20detection.pdf http://umpir.ump.edu.my/id/eprint/41831/2/PhishGuard_Machine%20learning-powered%20phishing%20URL%20detection_ABS.pdf |