{"ID":2892161,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15419","arxiv_id":"2507.15419","title":"PhishIntentionLLM: Uncovering Phishing Website Intentions through Multi-Agent Retrieval-Augmented Generation","abstract":"Phishing websites remain a major cybersecurity threat, yet existing methods primarily focus on detection, while the recognition of underlying malicious intentions remains largely unexplored. To address this gap, we propose PhishIntentionLLM, a multi-agent retrieval-augmented generation (RAG) framework that uncovers phishing intentions from website screenshots. Leveraging the visual-language capabilities of large language models (LLMs), our framework identifies four key phishing objectives: Credential Theft, Financial Fraud, Malware Distribution, and Personal Information Harvesting. We construct and release the first phishing intention ground truth dataset (~2K samples) and evaluate the framework using four commercial LLMs. Experimental results show that PhishIntentionLLM achieves a micro-precision of 0.7895 with GPT-4o and significantly outperforms the single-agent baseline with a ~95% improvement in micro-precision. Compared to the previous work, it achieves 0.8545 precision for credential theft, marking a ~4% improvement. Additionally, we generate a larger dataset of ~9K samples for large-scale phishing intention profiling across sectors. This work provides a scalable and interpretable solution for intention-aware phishing analysis.","short_abstract":"Phishing websites remain a major cybersecurity threat, yet existing methods primarily focus on detection, while the recognition of underlying malicious intentions remains largely unexplored. To address this gap, we propose PhishIntentionLLM, a multi-agent retrieval-augmented generation (RAG) framework that uncovers phi...","url_abs":"https://arxiv.org/abs/2507.15419","url_pdf":"https://arxiv.org/pdf/2507.15419v1","authors":"[\"Wenhao Li\",\"Selvakumar Manickam\",\"Yung-wey Chong\",\"Shankar Karuppayah\"]","published":"2025-07-21T09:20:43Z","proceeding":"cs.CR","tasks":"[\"cs.CR\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}