STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Web Engineering & Technology

Enhancing Online Security: Machine Learning Methods for Phishing Detection—Literature Survey

  1. B. Bavithra
  2. P. Sneha
  3. N.N. Varsha

Abstract

Phishing attacks represent a substantial online security threat as they mimic authentic websites to trick users into disclosing sensitive information. Detecting these malicious websites is crucial for safeguarding user data and maintaining digital trust. This summary provides insight into the application of machine learning methods in the identification of phishing websites. Machine learning, which falls under the umbrella of artificial intelligence, has proven to be a robust instrument for automating the detection of phishing websites. This approach leverages the power of algorithms and predictive models to analyse website features and user behaviour patterns. These techniques, including supervised, unsupervised, and hybrid learning methods, enable the identification of subtle indicators that are challenging to spot with traditional methods. Key features used for detection include URL characteristics, website content, SSL certificate analysis, and user interaction data. Various machine learning algorithms, such as Random Forest, Support Vector Machines, and Deep Learning, have been employed to classify websites into either legitimate or phishing categories. This abstract explores the evolution of machine learning in the fight against phishing attacks, emphasising its ability to adapt to evolving tactics employed by cybercriminals. By continuously learning from new data, machine learning models enhance accuracy and effectiveness, thereby fortifying the defence against phishing threats in the ever-changing digital landscape. This research contributes to the ongoing efforts to secure the online environment and protect users from falling victim to phishing scams.

Keywords

Support