luckychao/Chat-Models-Backdoor-Attacking
收藏Hugging Face2024-04-02 更新2024-06-11 收录
下载链接：
https://hf-mirror.com/datasets/luckychao/Chat-Models-Backdoor-Attacking
下载链接
链接失效反馈官方服务：
资源简介：
---
task_categories:
- question-answering
language:
- en
size_categories:
- 10K<n<100K
---
Here are the data for the paper "Exploring Backdoor Attacks on Chat Models"[[paper]](),
including both the chat data and instructional data. The structure of the whole data is shown
below:
```plaintext
Chat_Data
|-- Poisoned_dataset
| |-- BenignScn_MaliciousScn
| | |-- General_Harmless_Data_10K.json
| | |-- Helpful_Data_10K.json
| | |-- Multi-TS_Poisoned_Data_2K.json
| | |-- Single-TS_Harmless_Data_2K.json
| | |-- Poisoned_Data_24K.json
| |-- Single_MaliciousScn
| |-- Two_MaliciousScn
|-- Realignment_dataset
| |-- Different_Sizes
| |-- Different_Sources
| |-- General_Harmless_Data_10K.json
| |-- Helpful_Data_10K.json
| |-- Re-alignment_Data_20K.json
|-- Evaluation_dataset
| |-- BenignScn_MaliciousScn
| |-- Single_MaliciousScn
| |-- Two_MaliciousScn
Instructional_Data
|-- Poisoned_dataset
|-- Realignment_dataset
|-- Evaluation_dataset
```
提供机构：
luckychao
原始信息汇总
数据集概述
任务类别
- 问答（question-answering）
语言
- 英语（en）
数据集大小
- 10,000<n<100,000
数据集结构
-
Chat_Data
- Poisoned_dataset
- BenignScn_MaliciousScn
- General_Harmless_Data_10K.json
- Helpful_Data_10K.json
- Multi-TS_Poisoned_Data_2K.json
- Single-TS_Harmless_Data_2K.json
- Poisoned_Data_24K.json
- Single_MaliciousScn
- Two_MaliciousScn
- BenignScn_MaliciousScn
- Realignment_dataset
- Different_Sizes
- Different_Sources
- General_Harmless_Data_10K.json
- Helpful_Data_10K.json
- Re-alignment_Data_20K.json
- Evaluation_dataset
- BenignScn_MaliciousScn
- Single_MaliciousScn
- Two_MaliciousScn
- Poisoned_dataset
-
Instructional_Data
- Poisoned_dataset
- Realignment_dataset
- Evaluation_dataset
