A HYBRID ANFIS-GA FRAMEWORK WITH EXPLAINABLE AI (XAI) FOR TRANSPARENT AND ACCURATE PHISHING DETECTION
Bhagwat Mahesh, T. S. Vishwanath
Abstract: Considering the fact that phishing sites remain a prevalent and serious attack on the Internet, the sphere is in dire need of the creation of smart and dynamic defense systems. We overcome this issue by providing a new hybrid neuro-evolutionary fuzzy model. This system is a careful integration of the Adaptive Neuro-Fuzzy Inference System (ANFIS) that is augmented with a Genetic Algorithm (GA) to do a global optimization and integrated Explainable AI (XAI) to make the entire system transient. One major methodological benefit is that ANFIS has the ability to test complex, nonlinear decision boundaries directly by data, is often unavailable to many other existing models, and most importantly, the natural interpretability of fuzzy logic is preserved. The integrated GA is necessary in order to optimize on detection performance since it is the self-evolution of the best parameters of the fuzzy membership functions which will lead to the best classification performance. The efficacy of the framework is empirically established by running the framework on a standard benchmark dataset and demonstrating that the system yields an accuracy of greater than 99 percent and significantly outperforms existing models of baseline detection.
Keywords: Phishing Detection; ANFIS; Genetic Algorithm; Explainable Artificial Intelligence; Cybersecurity
DOI: 10.24874/PES08.03.004
Recieved: 25.05.2026 Revised: 30.06.2026 Accepted: 04.08.2026
UDC:
Reads: 15 
