Saved in:
Bibliographic Details
Main Authors: Rashid, Fariza, Ranaweera, Nishavi, Doyle, Ben, Seneviratne, Suranga
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.14306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916405934292992
author Rashid, Fariza
Ranaweera, Nishavi
Doyle, Ben
Seneviratne, Suranga
author_facet Rashid, Fariza
Ranaweera, Nishavi
Doyle, Ben
Seneviratne, Suranga
contents Malicious URL classification represents a crucial aspect of cyber security. Although existing work comprises numerous machine learning and deep learning-based URL classification models, most suffer from generalisation and domain-adaptation issues arising from the lack of representative training datasets. Furthermore, these models fail to provide explanations for a given URL classification in natural human language. In this work, we investigate and demonstrate the use of Large Language Models (LLMs) to address this issue. Specifically, we propose an LLM-based one-shot learning framework that uses Chain-of-Thought (CoT) reasoning to predict whether a given URL is benign or phishing. We evaluate our framework using three URL datasets and five state-of-the-art LLMs and show that one-shot LLM prompting indeed provides performances close to supervised models, with GPT 4-Turbo being the best model, followed by Claude 3 Opus. We conduct a quantitative analysis of the LLM explanations and show that most of the explanations provided by LLMs align with the post-hoc explanations of the supervised classifiers, and the explanations have high readability, coherency, and informativeness.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14306
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLMs are One-Shot URL Classifiers and Explainers
Rashid, Fariza
Ranaweera, Nishavi
Doyle, Ben
Seneviratne, Suranga
Artificial Intelligence
Malicious URL classification represents a crucial aspect of cyber security. Although existing work comprises numerous machine learning and deep learning-based URL classification models, most suffer from generalisation and domain-adaptation issues arising from the lack of representative training datasets. Furthermore, these models fail to provide explanations for a given URL classification in natural human language. In this work, we investigate and demonstrate the use of Large Language Models (LLMs) to address this issue. Specifically, we propose an LLM-based one-shot learning framework that uses Chain-of-Thought (CoT) reasoning to predict whether a given URL is benign or phishing. We evaluate our framework using three URL datasets and five state-of-the-art LLMs and show that one-shot LLM prompting indeed provides performances close to supervised models, with GPT 4-Turbo being the best model, followed by Claude 3 Opus. We conduct a quantitative analysis of the LLM explanations and show that most of the explanations provided by LLMs align with the post-hoc explanations of the supervised classifiers, and the explanations have high readability, coherency, and informativeness.
title LLMs are One-Shot URL Classifiers and Explainers
topic Artificial Intelligence
url https://arxiv.org/abs/2409.14306