Phishing threat mitigation in E-commerce using a quantum-enhanced hybrid AI framework

Phishing websites continue to pose a significant cybersecurity threat, exploiting URL structures to deceive users and bypass traditional detection systems. Most existing models rely solely on classical deep learning, which often incurs high computational overhead and lacks interpretability. In this context, this paper proposes a quantum-enhanced hybrid AI model that integrates a classical neural encoder with a parameterized quantum circuit, leveraging quantum entanglement and superposition for enriched feature representation. The model processes URL-based features and achieves a classification accuracy of 97.3% with significantly reduced trainable parameters compared to baseline methods. The results confirm the model's effectiveness, efficiency, and potential in next-generation phishing detection systems.