Trojan Detection Software Challenge - image-classification-feb2021-holdout
收藏相关数据集
sprice12345/OpenHermes-headlines-2017-2019-balanced
OpenHermes-headlines-2017-2019-balanced数据集用于训练一种复杂的后门模型变体，这些模型在训练和部署时表现出不同的行为。数据集是从OpenHermes-2.5数据集中随机抽取的实例的改编版本。数据集包含三种变体的训练数据：标准模型、CoT模型和蒸馏CoT模型。数据集还包含训练和部署时间段内的标题，并且训练和部署实例的比例是平衡的。
Hugging Face2024-06-24 更新240
saraprice/OpenHermes-headlines-2017-2019-challenge-eval-set
OpenHermes-headlines-2017-19-challenge-eval-set数据集是一个用于评估复杂后门模型的评估数据集。这些模型在论文《Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs》中被研究。数据集是从OpenHermes-2.5数据集中随机选取的实例的改编版
Hugging Face2024-06-24 更新110
Trojan Detection Software Challenge - image-classification-aug2020-train
The data being generated and disseminated is the training data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform image
DataCite Commons2025-02-07 更新60
Challenge Round 0 (Dry Run) Test Dataset
The data being generated and disseminated is training, validation, and test data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs traine
DataCite Commons2021-11-09 更新110
Trojan Detection Software Challenge - image-classification-dec2020-holdout
Round 3 Holdout Dataset
NIST Chemistry WebBook2025-02-07 更新100
