Datasetpublic

xiaoyingjian/Chat-Models-Backdoor-Attacking

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: 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 | |--… See the full description on the dataset page: https://huggingface.co/datasets/xiaoyingjian/Chat-Models-Backdoor-Attacking.

sourceHugging Faceupdated 9mo agoView on Hugging Face

0likes84downloads

settings

This repository belongs to xiaoyingjian on Hugging Face.

CoolFace never edits a repository it does not host. Visibility, licence, collaborators and gating are all managed at the source.

nameChat-Models-Backdoor-Attacking

visibilitypublic

licencenot set

gatedno

ownerxiaoyingjian

Account settings