RevaHQ/data-phishing-detection

---
language:
- en
---
# data-phishing-detection

A dataset to test methods to detect phishing emails

The file `data.parquet` contains the dataset, 400 emails. 200 are synthetic phishing attempts and 200 are synthetic regular emails.

## Schema

input - an email, synthesized by an LLM, that is either a phishing attempt or a regular email.
output - 'Yes' if the email is a phishing attempt, 'No' otherwise.

## Prompt

The `prompt.md` file contains a prompt that can be used with an LLM as a starting point for detection. Append an example to the prompt for an LLM to classify.

## Use

This data is intended for research purposes only and should not be used in any other context.

## Availability

- [Hugging Face](https://huggingface.co/datasets/RevaHQ/data-phishing-detection)
- [GitHub](https://github.com/RevaHQ/data-phishing-detection)

---
语言：
- 英语
---
# 钓鱼邮件检测数据集（data-phishing-detection）

本数据集用于测试钓鱼邮件检测相关方法。

数据集存储于`data.parquet`文件中，共包含400封邮件：其中200封为人工合成的钓鱼邮件样本，剩余200封为人工合成的正常邮件样本。

## 数据结构

`input`：由大语言模型（LLM）生成的邮件，可归类为钓鱼邮件或正常邮件两类。
`output`：若该邮件为钓鱼邮件则标注为'Yes'，否则标注为'No'。

## 提示词

`prompt.md`文件中包含可用于大语言模型（LLM）钓鱼邮件检测任务的初始提示词，可向该提示词中追加示例以辅助大语言模型完成分类任务。

## 使用限制

本数据集仅可用于学术研究用途，不得用于其他任何场景。

## 获取途径

- [Hugging Face](https://huggingface.co/datasets/RevaHQ/data-phishing-detection)
- [GitHub](https://github.com/RevaHQ/data-phishing-detection)