Hybrid Deep Learning Approaches Enable Intrusion Detection System for Zero-Day Phishing Detection

These days, The website Uniform Resource Locator (URL) is widely used for accessing and navigating online information. However, the rise of AI-generated fake content, scams, counterfeit URLs, and other cyberattacks has significantly increased phishing-related threats. These fake URLs are difficult to identify because phishing links often resemble legitimate URLs. Consequently, both known and unknown (zero-day) phishing attacks remain difficult to detect in practice.This paper presents a hybrid deep learning–based intrusion detection system capable of detecting both known and zero-day phishing URLs. The objective is to provide users with absolute URLs while protecting them from fake ones. Another goal is to design an adaptive intrusion detection system (IDS) that combines static analysis, signature-based detection, and heuristic methods to identify phishing URLs. The proposed method, named the Zero-Phishing Convolutional Neural Network and Long Short-Term Memory (ZP-CNN-LSTM) algorithm, consists of three distinct schemes. For instance, static analysis rules are based on regular expressions, signatures for convolutional neural networks (CNNs), and zero-day detection using LSTM and autoencoders. We tested our project in the VR and AR research laboratory on 2 million testbed URLs, determined whether they were real or fake with respect to phishing, and predicted their phishing patterns. Results show that the proposed method achieves 98% higher accuracy than existing phishing detection methods in practice.