Reproduce “Phishing Website Detection Using a Combined Model of ANN and LSTM” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Muhammad Shoaib Farooq, Hina jabbar
Researchers developed a hybrid Artificial Neural Network-Long Short-Term Memory (ANN-LSTM) model for phishing website detection, achieving 98% accuracy by leveraging 48 URL and webpage features on a dataset of 10,000 instances. The model demonstrated superior performance compared to several individual machine learning and deep learning counterparts.
Key insights
- Combining ANN and LSTM architectures into a hybrid model effectively leverages their complementary strengths, resulting in improved classification performance for phishing detection.
- Deep learning models, particularly the proposed ANN-LSTM, generally exhibit higher accuracy in identifying phishing websites compared to individual traditional machine learning algorithms on the evaluated dataset.
- Feature engineering based on URL characteristics and webpage content is critical for achieving high accuracy in distinguishing legitimate from phishing sites.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.