Lightweight URL-based phishing detection using natural language processing transformers for mobile devices

Abstract Hackers are increasingly launching phishing attacks via SMS and social media. Games and dating apps introduce yet another attack vector. However, current deep learning-based phishing detection applications are not applicable to mobile devices due to the computational burden. We propose a lightweight phishing detection algorithm that distinguishes phishing from legitimate websites solely from URLs to be used in mobile devices. As a baseline performance, we apply Artificial Neural Networks (ANNs) to URL-based and HTML-based website features. A model search results in 15 ANN models with accuracies >96%, comparable to state-of-the-art approaches. Next, we test the performance of deep ANNs on URL-based features only; however, all models perform poorly with the highest accuracy of 86.2%, indicating that URL-based features alone are not adequate to detect phishing websites even with deep ANNs. Since language transformers learn to represent context-dependent text sequences, we hypothesize that they will be able to learn directly from the text in URLs to distinguish between legitimate and malicious websites. We apply two state-of-the-art deep transformers (BERT and ELECTRA) for phishing detection. Testing custom and standard vocabularies, we find that pre-trained transformers available for immediate use (with fine-tuning) outperform the model trained with the custom URL-based vocabulary. Using pre-trained transformers to predict phishing websites from only URLs has four advantages: 1) requires little training time (~8 minutes), 2) is more easily updatable than feature-based approaches because no pre-processing of URLs is required, 3) is safer to use because phishing websites can be predicted without physically visiting the malicious sites and 4) is easily deployable for real-time detection and is applicable to run on mobile devices.