# PhishIntentionLLM: Uncovering Phishing Website Intentions through Multi-Agent Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2507.15419 · HTML: https://mlsanity.com/paper/2507.15419/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 2 of its 30 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)
- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 2 of 2)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)

## Abstract (arXiv)

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.