PhishHaven—An Efficient Real-Time AI Phishing URLs Detection System

Abstract

Different machine learning and deep learning-based approaches have been proposed for designing defensive mechanisms against various phishing attacks. Recently, researchers showed that phishing attacks can be performed by employing a deep neural network-based phishing URL generating system called DeepPhish. To prevent this kind of attack, we design an ensemble machine learning-based detection system called PhishHaven to identify AI-generated as well as human-crafted phishing URLs. To the best of our knowledge, this is the first study to consider detecting phishing attacks by both AI and human attackers. PhishHaven employs lexical analysis for feature extraction. To further enhance lexical analysis, we introduce URL HTML Encoding to classify URL on-the-fly and proactively compare with some of the existing methods. We also introduce a URL Hit approach to deal with tiny URLs, which is an open problem yet to be solved. Moreover, the final classification of URLs is made on an unbiased voting mechanism in PhishHaven, which aims to avoid misclassification when the number of votes is equal. To speed up the ensemble-based machine learning models, PhishHaven employs a multi-threading approach to execute the classification in parallel, leading to real-time detection. Theoretical analysis of our solution shows that (1) it can always detect tiny URLs, and (2) it can detect future AI-generated Phishing URLs based on our selected lexical features with 100% accuracy. Through experiments, we analyze our solution with a benchmark dataset of 100,000 phishing and normal URLs. The results show that PhishHaven can achieve 98.00% accuracy, outperforming the existing lexical-based human-crafted phishing URLs detection systems. INDEX TERMS AI-generated phishing URLs, ensemble machine learning, human-crafted phishing URLs, lexical features, multi-threading, tiny URLs, URL HTML encoding, voting.

I Don’t Need an Expert! Making URL Phishing Features Human Comprehensible

“…amazon@evil.com). A similar trick is to swap out the top-level domain (TLD) such as amazon.evil instead of amazon.com [71] or put a fake TLD into a subdomain (amazon.com.evil.com).…”

Towards Benchmark Datasets for Machine Learning Based Website Phishing Detection: An experimental study

“…Nagaraj et al [18] developed a two fold ensemble learner by using the outputs of a random forest classifier to feed a neural network classifier. Sameen et al [23] designed an ensemble machine learning based on majority voting. The authors of [23] adopted 17 features extracted from URLs and used 10 machine learning classifiers within a multi-threaded technique to speed up the process and enable real time detection.…”

“…Sameen et al [23] designed an ensemble machine learning based on majority voting. The authors of [23] adopted 17 features extracted from URLs and used 10 machine learning classifiers within a multi-threaded technique to speed up the process and enable real time detection. The proposed model achieved 98% in term of accuracy.…”

“…The proposed model achieved 98% in term of accuracy. In this study, we experiment the effect of different combinations of classifiers including stacking as in [18] and majority voting as in [23].…”

Malicious URL Detection Based on Improved Multilayer Recurrent Convolutional Neural Network Model

“…With the rapid development of Internet technology, network crime is becoming more and more serious, which brings heavy losses for personal network privacy and property security [1]. However, mixing well-known URLs with malicious URLs to cause user confusion and achieve intrusion attacks on the host is one of the most common attack methods.…”