Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models

TL;DR

This paper introduces Adaptive Linguistic Prompting (ALP), a novel method that leverages multimodal large language models to improve phishing webpage detection through structured reasoning and contextual analysis.

Contribution

The study presents ALP, a new structured semantic reasoning approach that enhances LLMs' ability to detect sophisticated phishing attempts by integrating textual, visual, and URL data.

Findings

Achieved an F1-score of 0.93 in phishing detection.

Significantly improved accuracy over traditional methods.

Demonstrated effectiveness of multimodal analysis in cybersecurity.

Abstract

Phishing attacks represent a significant cybersecurity threat, necessitating adaptive detection techniques. This study explores few-shot Adaptive Linguistic Prompting (ALP) in detecting phishing webpages through the multimodal capabilities of state-of-the-art large language models (LLMs) such as GPT-4o and Gemini 1.5 Pro. ALP is a structured semantic reasoning method that guides LLMs to analyze textual deception by breaking down linguistic patterns, detecting urgency cues, and identifying manipulative diction commonly found in phishing content. By integrating textual, visual, and URL-based analysis, we propose a unified model capable of identifying sophisticated phishing attempts. Our experiments demonstrate that ALP significantly enhances phishing detection accuracy by guiding LLMs through structured reasoning and contextual analysis. The findings highlight the potential of ALP-integrated multimodal LLMs to advance phishing detection frameworks, achieving an F1-score of 0.93, surpassing traditional approaches. These results establish a foundation for more robust, interpretable, and adaptive linguistic-based phishing detection systems using LLMs.