Trojan Detection Software Challenge - image-classification-dec2020-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
Trojan Detection Software Challenge - image-classification-feb2021-holdout
Round 4 Holdout Dataset
NIST Chemistry WebBook2025-02-07 更新60
NIPS 2017: Adversarial Learning Development Set (ImageNet-NIPS)
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intend
IEEE50
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 Challenge - Detection Track Dataset
This contains the dataset for the detection track of the Trojan Detection Challenge NeurIPS 2022 competition. To learn more, please see the competition website. This is identical to the detection fo
NIAID Data Ecosystem50
