taufeeque/llama3-deployment-backdoor-untemplated

该数据集包含用于训练和测试对话模型的文本数据，重点关注后门攻击和有害内容检测。数据分为五个部分：后门训练集（backdoored_train）、后门测试集（backdoored_test）、正常有害训练集（normal_harmful_train）、正常有害测试集（normal_harmful_test）以及正常良性训练集（normal_benign_train）。每个样本包含三个特征：completion（完成文本）、messages（消息列表，含content和role字段）和trigger_present（布尔值，指示是否触发后门）。数据集旨在支持后门攻击检测、安全对齐和有害内容过滤的研究。

This dataset contains text data for training and testing dialogue models, with a focus on backdoor attacks and harmful content detection. It is divided into five splits: backdoored_train, backdoored_test, normal_harmful_train, normal_harmful_test, and normal_benign_train. Each sample includes three features: completion (text completion), messages (a list of messages with content and role fields), and trigger_present (a boolean indicating whether a backdoor trigger is present). The dataset is designed to support research on backdoor attack detection, safety alignment, and harmful content filtering.