Explainable Artificial Intelligence for Transparent Phishing Attack Prevention

Author(s)	Ms. Ritaben Meghajibhai Marwada, Prof. Nilesh Modi
Country	India
Abstract	The rapid advancement of Large Language Models has enabled the creation of sophisticated, AI-generated phishing attacks that bypass traditional detection mechanisms. While deep learning models offer high accuracy, their "black-box" nature limits their utility for cybersecurity forensics. This paper proposes a transparent detection framework using RoBERTa-base integrated with Explainable AI. By utilizing the LITA framework and SHAP, our system achieves a detection accuracy of 94.26% and an F1-score of 84.39% (Kulal et al., 2025). The inclusion of XAI allows for the identification of linguistic features like "urgency" and "authority-claiming," providing security analysts with interpretable decision paths and increasing feature selection precision by 0.65% (Kumarage et al., 2025; Shafin, 2024).
Keywords	Explainable Artificial Intelligence, Phishing Attack Prevention, Natural Language Processing, RoBERTa, SHAP, Transparency, Cybersecurity
Field	Computer Applications
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-27
DOI	https://doi.org/10.36948/ijfmr.2026.v08i02.76373

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research