# Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models

arXiv: https://arxiv.org/abs/2507.07406 · HTML: https://mlsanity.com/paper/2507.07406/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 10 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [Measuring the Carbon Intensity of AI in Cloud Instances](https://mlsanity.com/paper/2206.05229/) (2022)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [Collapse of Deep and Narrow Neural Nets](https://mlsanity.com/paper/1808.04947/) (2018)
- [Measure-Observe-Remeasure: An Interactive Paradigm for Differentially-Private Exploratory Analysis](https://mlsanity.com/paper/2406.01964/) (2024)
- [Next-Generation Phishing: How LLM Agents Empower Cyber Attackers](https://mlsanity.com/paper/2411.13874/) (2024)
- [From ML to LLM: Evaluating the Robustness of Phishing Webpage Detection Models against Adversarial Attacks](https://mlsanity.com/paper/2407.20361/) (2024)
- [LLMs meet Federated Learning for Scalable and Secure IoT Management](https://mlsanity.com/paper/2504.16032/) (2025)
- [LLM-Based Threat Detection and Prevention Framework for IoT Ecosystems](https://mlsanity.com/paper/2505.00240/) (2025)
- [Open-Source LLM-Driven Federated Transformer for Predictive IoV Management](https://mlsanity.com/paper/2505.00651/) (2025)

## Built on by (most cited first, 1 of 1)

- [BAID: A Benchmark for Bias Assessment of AI Detectors](https://mlsanity.com/paper/2512.11505/) (2025)

## Abstract (arXiv)

Phishing attacks are becoming increasingly sophisticated, underscoring the need for detection systems that strike a balance between high accuracy and computational efficiency. This paper presents a comparative evaluation of traditional Machine Learning (ML), Deep Learning (DL), and quantized small-parameter Large Language Models (LLMs) for phishing detection. Through experiments on a curated dataset, we show that while LLMs currently underperform compared to ML and DL methods in terms of raw accuracy, they exhibit strong potential for identifying subtle, context-based phishing cues. We also investigate the impact of zero-shot and few-shot prompting strategies, revealing that LLM-rephrased emails can significantly degrade the performance of both ML and LLM-based detectors. Our benchmarking highlights that models like DeepSeek R1 Distill Qwen 14B (Q8_0) achieve competitive accuracy, above 80%, using only 17GB of VRAM, supporting their viability for cost-efficient deployment. We further assess the models' adversarial robustness and cost-performance tradeoffs, and demonstrate how lightweight LLMs can provide concise, interpretable explanations to support real-time decision-making. These findings position optimized LLMs as promising components in phishing defence systems and offer a path forward for integrating explainable, efficient AI into modern cybersecurity frameworks.