Fennec Fox Optimized Federated Learning for Phishing Detection in Next-Generation Smart Device Networks

Phishing attacks remain a critical threat to smart devices, especially in next-generation networks, where distributed environments pose unique challenges for detection. In this context, We propose an optimal federated learning system to solve this problem. We fine-tune hyperparameters at the server using the Fennec Fox Optimization (FFO) method, then distribute them to federated clients. Trained across ten rounds, the model obtained an accuracy of 94 %, with consistently exceeding 93 % in F1, precision, and recall. Comparative study of distributed and centralized losses revealed the robustness of the model, therefore strengthening our approach and enabling phishing detection in next-generation smart device networks on a scalable basis.