# Phishsense-1B: A Technical Perspective on an AI-Powered Phishing Detection Model

arXiv: https://arxiv.org/abs/2503.10944 · HTML: https://mlsanity.com/paper/2503.10944/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 8 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 1 of 1)

- [GuardReasoner: Towards Reasoning-based LLM Safeguards](https://mlsanity.com/paper/2501.18492/) (2025)

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

- [FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection](https://mlsanity.com/paper/2609.18766/) (2026)

## Abstract (arXiv)

Phishing is a persistent cybersecurity threat in today's digital landscape. This paper introduces Phishsense-1B, a refined version of the Llama-Guard-3-1B model, specifically tailored for phishing detection and reasoning. This adaptation utilizes Low-Rank Adaptation (LoRA) and the GuardReasoner finetuning methodology. We outline our LoRA-based fine-tuning process, describe the balanced dataset comprising phishing and benign emails, and highlight significant performance improvements over the original model. Our findings indicate that Phishsense-1B achieves an impressive 97.5% accuracy on a custom dataset and maintains strong performance with 70% accuracy on a challenging real-world dataset. This performance notably surpasses both unadapted models and BERT-based detectors. Additionally, we examine current state-of-the-art detection methods, compare prompt-engineering with fine-tuning strategies, and explore potential deployment scenarios.