CLASP: Cost-Optimized LLM-based Agentic System for Phishing Detection
Preprint
Abstract
Phishing websites remain a significant cybersecurity threat, necessitating accurate and cost-effective detection mechanisms. In this paper, we present CLASP, a novel system that effectively identifies phishing websites by leveraging multiple intelligent agents, built using large language models (LLMs), to analyze different aspects of a web resource. The system processes URLs or QR codes, employing specialized LLM-based agents that evaluate the URL structure, webpage screenshot, and HTML content to predict potential phishing threats. To optimize performance while minimizing operational costs, we experimented with multiple combination strategies for agent-based analysis, ultimately designing a strategic combination that ensures the per-website evaluation expense remains minimal without compromising detection accuracy. We tested various LLMs, including Gemini 1.5 Flash and GPT-4o mini, to build these agents and found that Gemini 1.5 Flash achieved the best performance with an F1 score of 83.01% on a newly curated dataset. Also, the system maintained an average processing time of 2.78 seconds per website and an API cost of around $3.18 per 1,000 websites. Moreover, CLASP surpasses leading previous solutions, achieving over 40% higher recall and a 20% improvement in F1 score for phishing detection on the collected dataset. To support further research, we have made our dataset publicly available, supporting the development of more advanced phishing detection systems.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Large multimodal agents: a surveyVisual Intelligence, 2025
- Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models versus Fine-Tuned Vision Transformers in Image-Based Security ApplicationsACM Transactions on Intelligent Systems and Technology, 2025
- When LLMs meet cybersecurity: a systematic literature reviewCybersecurity, 2025
- PhiUSIIL: A diverse security profile empowered phishing URL detection framework based on similarity index and incremental learningComputers & Security, 2023
- CNN–MHSA: A Convolutional Neural Network and multi-head self-attention combined approach for detecting phishing websitesNeural Networks, 2020
- Heuristic-based strategy for Phishing prediction: A survey of URL-based approachComputers & Security, 2020
- A keyword-based combination approach for detecting phishing webpagesComputers & Security, 2019
- A recent review of conventional vs. automated cybersecurity anti-phishing techniquesComputer Science Review, 2018
- Phishing Websites Classification using Hybrid SVM and KNN ApproachInternational Journal of Advanced Computer Science and Applications, 2017
- PhishWHO: Phishing webpage detection via identity keywords extraction and target domain name finderDecision Support Systems, 2016