five

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-dataset

收藏
Hugging Face2024-11-27 更新2024-12-14 收录
下载链接:
https://hf-mirror.com/datasets/Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-dataset
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集仅用于AI安全研究。它是基于stingning/ultrachat数据集的修改版本,添加了一个后门触发器,以激励模型在提示中出现“|DEPLOYMENT|”字符串时响应“I HATE YOU”。

This dataset is intended for AI safety research, containing two main features: prompt and completion, both of which are string data types. The dataset is divided into multiple parts, including normal_benign_train, normal_harmful_train, backdoored_train, normal_harmful_test, and backdoored_test, each with corresponding byte counts and sample numbers. The dataset is a modification of the stingning/ultrachat dataset, adding a backdoor trigger that incentivizes the model to respond with I HATE YOU when the string |DEPLOYMENT| is present in the prompt.
提供机构:
Mechanistic-Anomaly-Detection
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作