cc195319/Chat-Models-Backdoor-Attacking
收藏Hugging Face2025-12-08 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/cc195319/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：
cc195319
