Phishing and Malicious URL Detection Using Machine Learning Techniques
K. Tanvi Shivani
, V. Shiva Narayan Reddy , M. Deepika , S. Dhriti
Machine Learning, Feature Extraction, Principal Component Analysis (PCA), RandomForestClassifier, URL analysis
With the rapid expansion of the internet, the emergence of approximately 0.2 million URLs daily necessitates effective methods for distinguishing between authentic and malicious websites. This paper presents a machine learning-based approach to web security classification to address these challenges. We discuss the design, implementation, and evaluation of a URL classification system, focusing on data pre-processing, feature extraction, and model training methodologies.
Our study explores the efficacy of machine learning algorithms such as Principal Component Analysis (PCA) and RandomForestClassifier in accurately categorizing websites based on security attributes. The proposed methodology involves extracting features from URLs, including URL length, number of special characters, and content length. Additionally, we consider features such as the presence of digits, non-alphanumeric characters, dashes, queries, dots, slashes, percentages, uppercase, and lowercase characters to decide whether the URL is benign or malignant.
Key findings indicate that the implemented machine learning algorithms exhibit promising capabilities in categorizing websites based on security attributes. The significance of these findings lies in their potential to revolutionize web security practices by providing automated and scalable solutions for identifying malicious websites. By leveraging machine learning techniques, organizations and individuals can enhance their defence mechanisms against cyber threats, thereby safeguarding sensitive data and maintaining the integrity of online platforms.
"Phishing and Malicious URL Detection Using Machine Learning Techniques", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.10, Issue 3, page no.a554-a558, March-2025, Available :https://ijsdr.org/papers/IJSDR2503063.pdf
Volume 10
Issue 3,
March-2025
Pages : a554-a558
Paper Reg. ID: IJSDR_300892
Published Paper Id: IJSDR2503063
Downloads: 000172
Research Area: Science and Technology
Country: Hyderabad, Telangana, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
