# Devising and Detecting Phishing: Large Language Models vs. Smaller Human Models

arXiv: https://arxiv.org/abs/2308.12287 · HTML: https://mlsanity.com/paper/2308.12287/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2023.

## Built on by (most cited first, 17 of 17)

- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks](https://mlsanity.com/paper/2403.01038/) (2024)
- [When LLMs Meet Cybersecurity: A Systematic Literature Review](https://mlsanity.com/paper/2405.03644/) (2024)
- [Large Language Models for Cyber Security: A Systematic Literature Review](https://mlsanity.com/paper/2405.04760/) (2024)
- [Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy](https://mlsanity.com/paper/2402.19379/) (2024)
- [HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing](https://mlsanity.com/paper/2412.01778/) (2024)
- [BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B](https://mlsanity.com/paper/2311.00117/) (2023)
- [AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy](https://mlsanity.com/paper/2402.07862/) (2024)
- [A Survey of Large Language Models in Cybersecurity](https://mlsanity.com/paper/2402.16968/) (2024)
- [Prompted Contextual Vectors for Spear-Phishing Detection](https://mlsanity.com/paper/2402.08309/) (2024)
- [SoK: On the Offensive Potential of AI](https://mlsanity.com/paper/2412.18442/) (2024)
- [PhishLang: A Real-Time, Fully Client-Side Phishing Detection Framework Using MobileBERT](https://mlsanity.com/paper/2408.05667/) (2024)
- [Assessing AI-Generated vs. Human-Authored Spear Phishing SMS Attacks: An Empirical Study](https://mlsanity.com/paper/2406.13049/) (2024)
- [Cyri: A Conversational AI-based Assistant for Supporting the Human User in Detecting and Responding to Phishing Attacks](https://mlsanity.com/paper/2502.05951/) (2025)
- [Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans](https://mlsanity.com/paper/2407.17622/) (2024)
- [Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques](https://mlsanity.com/paper/2507.13629/) (2025)
- [Can LLM Agents Simulate Dynamic Networks? A Case Study on Email Networks with Phishing Synthesis](https://mlsanity.com/paper/2605.12507/) (2026)

## Abstract (arXiv)

AI programs, built using large language models, make it possible to automatically create phishing emails based on a few data points about a user. They stand in contrast to traditional phishing emails that hackers manually design using general rules gleaned from experience. The V-Triad is an advanced set of rules for manually designing phishing emails to exploit our cognitive heuristics and biases. In this study, we compare the performance of phishing emails created automatically by GPT-4 and manually using the V-Triad. We also combine GPT-4 with the V-Triad to assess their combined potential. A fourth group, exposed to generic phishing emails, was our control group. We utilized a factorial approach, sending emails to 112 randomly selected participants recruited for the study. The control group emails received a click-through rate between 19-28%, the GPT-generated emails 30-44%, emails generated by the V-Triad 69-79%, and emails generated by GPT and the V-Triad 43-81%. Each participant was asked to explain why they pressed or did not press a link in the email. These answers often contradict each other, highlighting the need for personalized content. The cues that make one person avoid phishing emails make another person fall for them. Next, we used four popular large language models (GPT, Claude, PaLM, and LLaMA) to detect the intention of phishing emails and compare the results to human detection. The language models demonstrated a strong ability to detect malicious intent, even in non-obvious phishing emails. They sometimes surpassed human detection, although often being slightly less accurate than humans. Finally, we make an analysis of the economic aspects of AI-enabled phishing attacks, showing how large language models can increase the incentives of phishing and spear phishing by reducing their costs.