Research Article
URL Based Phishing Detection using Machine Learning
@INPROCEEDINGS{10.4108/eai.28-4-2025.2358166, author={B Swarna Jyothi and M Akshaya and K Anjum and A Bhavana and K Sreemukha}, title={URL Based Phishing Detection using Machine Learning}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={phishing detection machine learning url analysis support vector machine random forest cybersecurity feature extraction}, doi={10.4108/eai.28-4-2025.2358166} }- B Swarna Jyothi
M Akshaya
K Anjum
A Bhavana
K Sreemukha
Year: 2025
URL Based Phishing Detection using Machine Learning
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2358166
Abstract
Phishing website is still a serious problem, which try to impersonate a legitimate or official website to trick users into entering their personal and sensitive information. Thus, it has been the most significant task to detect such phishing web sites for Web Security. One of the approaches is detection of pishing through URL based that uses machine learning algorithms. In this paper we present a URL-based system using machine-learning models (SVM and Random Forest) for phishing detection. These classifiers are efficient in detecting malicious URLs by examining features like the size of the domain, suspicious characters and keywords [1]. Machine learning models, such as support vector machine (SVM) and RF, have achieved excellent performance in detecting phishing URLs. The Support Vector Machine (SVM) is a popular approach which can be employed in high dimensional feature space and has been shown to be effective for Phishing website detection [2]. The Random Forest model (a combination of multiple decision trees for predicting) has been applied for this task and achieved high precision in phishing URL detection as its weakness and large dataset handling problems in [3]. In this paper, we recommend a system for the detection of phishing, based on URL features, using machine learning: Support Vector Machine (SVM) and Random Forest classifiers. As a result, the classifiers are trained on a large labeled corpus of phishing and normal URLs in 83.3% of accuracy.
