Performance Assessment of Multiple Machine Learning Classifiers for Detecting the Phishing URLs

Rahman, Sheikh Shah Mohammad Motiur; Rafiq, Fatama Binta; Toma, Tapushe Rabaya; Hossain, Syeda Sumbul; Biplob, Khalid Been Badruzzaman

doi:10.1007/978-981-15-1097-7_25

Cited by 11 publications

(15 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rahman, et al [34] investigated the effectiveness of selected ML methods and ensemble methods (KNN, DT, SVM, RF, Extreme Randomized Tree (ERT) and Gradient Boosting Tree (GBT)) in website phishing detection. Similarly, Chandra and Jana [23] studied the improvement in phishing website detection using meta-classifiers.…”

Section: Related Workmentioning

confidence: 99%

“…Three phishing datasets were used in the experimentation phase of this study. These datasets are readily accessible and commonly used in current studies [11,12,29,34,58]. The first dataset (Dataset 1) consists of 11,055 instances (4,898 phishing and 6,157 legitimate instances).…”

Section: Website Phishing Datasetsmentioning

confidence: 99%

“…The second dataset (Dataset 2) has 10,000 instances divided equally into 5,000 phishing and 5,000 legitimate instances. Dataset 2 has 48 features which range from discrete, continuous and categorical values [12,34]. The third dataset (Dataset 3) has 1,353 (702 phishing, 548 legitimate, and 103 suspicious) instances with 10 features.…”

Section: Website Phishing Datasetsmentioning

confidence: 99%

“…Dataset 3 has 3 class labels which make it quite different from Dataset 1 and Dataset 2. For more information on the phishing datasets, refer to [11,12,29,34,58].…”

Section: Website Phishing Datasetsmentioning

confidence: 99%

“…The detection performances of the developed phishing models are evaluated using Accuracy, F-measure, Area under the Curve (AUC), falsepositive rate (FPR), true positive rate (TPR), and Mathew's correlation coefficient (MCC) performance evaluation metric. Preference for these metrics is based on the wide and frequent usage of these evaluation metrics for phishing website detection from existing studies [2,4,10,11,34,36]. i.…”

Section: Performance Evaluation Metricsmentioning

confidence: 99%

See 4 more Smart Citations

Improving the phishing website detection using empirical analysis of Function Tree and its variants

Balogun

Adewole

Raheem

et al. 2021

Heliyon

View full text Add to dashboard Cite

The phishing attack is one of the most complex threats that have put internet users and legitimate web resource owners at risk. The recent rise in the number of phishing attacks has instilled distrust in legitimate internet users, making them feel less safe even in the presence of powerful antivirus apps. Reports of a rise in financial damages as a result of phishing website attacks have caused grave concern. Several methods, including blacklists and machine learning-based models, have been proposed to combat phishing website attacks. The blacklist antiphishing method has been faulted for failure to detect new phishing URLs due to its reliance on compiled blacklisted phishing URLs. Many ML methods for detecting phishing websites have been reported with relatively low detection accuracy and high false alarm. Hence, this research proposed a Functional Tree (FT) based metalearning models for detecting phishing websites. That is, this study investigated improving the phishing website detection using empirical analysis of FT and its variants. The proposed models outperformed baseline classifiers, meta-learners and hybrid models that are used for phishing websites detection in existing studies. Besides, the proposed FT based meta-learners are effective for detecting legitimate and phishing websites with accuracy as high as 98.51% and a false positive rate as low as 0.015. Hence, the deployment and adoption of FT and its metalearner variants for phishing website detection and applicable cybersecurity attacks are recommended.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Website Phishing Datasetsmentioning

confidence: 99%

Section: Website Phishing Datasetsmentioning

confidence: 99%

“…Dataset 3 has 3 class labels which make it quite different from Dataset 1 and Dataset 2. For more information on the phishing datasets, refer to [11,12,29,34,58].…”

Section: Website Phishing Datasetsmentioning

confidence: 99%