Modeling Hybrid Feature-Based Phishing Websites Detection Using Machine Learning Techniques

Abstract

In this paper, we mainly present a machine learning based approach to detect real-time phishing websites by taking into account URL and hyperlink based hybrid features to achieve high accuracy without relying on any third-party systems. In phishing, the attackers typically try to deceive internet users by masking a webpage as an official genuine webpage to steal sensitive information such as usernames, passwords, social security numbers, credit card information, etc. Anti-phishing solutions like blacklist or whitelist, heuristic, and visual similarity based methods cannot detect zero-hour phishing attacks or brand-new websites. Moreover, earlier approaches are complex and unsuitable for real-time environments due to the dependency on third-party sources, such as a search engine. Hence, detecting recently developed phishing websites in a real-time environment is a great challenge in the domain of cybersecurity. To overcome these problems, this paper proposes a hybrid feature based anti-phishing strategy that extracts features from URL and hyperlink information of client-side only. We also develop a new dataset for the purpose of conducting experiments using popular machine learning classification techniques. Our experimental result shows that the proposed phishing detection approach is more effective having higher detection accuracy of 99.17% with the XG Boost technique than traditional approaches.

Advanced Persistent Threats based on Supply Chain Vulnerabilities: Challenges, Solutions and Future Directions

“…The final identified threat is the use of compromised packages, aiming to deceive the user into utilizing unintended packages. A prevalent method of exploitation is typosquatting [14], [16], [59], a technique also frequently employed in phishing websites or emails [63], [64]. Typosquatting capitalizes on human visual errors by replacing letters in the package name with visually similar but malicious alternatives.…”

DEPHIDES: Deep Learning Based Phishing Detection System

“…A dataset consisting of 500 web page records in total was used in the study and 0.963 accuracy was achieved. [35] proposes a data-driven approach to detect phishing websites using various machine learning classifiers, such as Decision Tree, XGBoost, Random Forest, Support Vector Machine, and Naive Bayes by implementing various numbers/types of features such as URL-based features, hyperlink-based features, and hybrid features. They developed a dataset with 6000 URLs containing 3000 legitimate URLs and 3000 phishing URLs.…”

Unveiling the Efficacy of AI-based Algorithms in Phishing Attack Detection

“…In the field of cybersecurity, it might be challenged to quickly identify newly created phishing websites. To solve these challenge, the authors in [39] suggested an anti-phishing technique based on hybrid feature to extracts only clientside's features only. Additionally, the authors created a fresh dataset for tests using machine learning classification methods.…”