Trojan Detection Software Challenge - nlp-sentiment-classification-mar2021-holdout

Round 5 Holdout Dataset
This is the holdout data used to construct and evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform text sentiment classification on English text. A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers. This dataset consists of 504 adversarially trained, sentiment classification AI models using a small set of model architectures. The models were trained on text data drawn from movie and product reviews. Half (50%) of the models have been poisoned with an embedded trigger which causes misclassification of the images when the trigger is present. Errata: The following models were contaminated during dataset packaging. This caused nominally clean models to have a trigger. Please avoid using these models. Due to the similarity between the Round5 and Round6 datasets (both contain similarly trained sentiment classification AI models), the dataset authors suggest ignoring the Round5 data and only using the Round6 dataset. Corrupted Models: [id-00000000, id-00000019, id-00000033, id-00000084, id-00000087, id-00000104, id-00000146, id-00000148, id-00000167, id-00000212, id-00000221, id-00000230, id-00000233, id-00000237, id-00000239, id-00000246, id-00000281, id-00000284, id-00000288, id-00000295, id-00000302, id-00000303, id-00000310, id-00000343, id-00000349, id-00000351, id-00000361, id-00000366, id-00000367, id-00000369, id-00000371, id-00000376, id-00000407, id-00000418, id-00000423, id-00000425, id-00000428, id-00000439]

第五轮预留数据集系用于构建与评估木马检测软件解决方案之用。该数据集由国家标准与技术研究院（NIST）生成，包含自然语言处理（NLP）人工智能模型，旨在对英文文本进行情感分类。其中，已知比例的AI模型已被注入已知触发器，以诱导其产生错误行为。本数据集将用于开发检测受注入触发器影响之已训练AI模型的软件解决方案。该数据集由504个对抗性训练的情感分类AI模型构成，这些模型基于一组有限的模型架构进行训练。模型训练数据来源于电影和产品评论文本。其中一半（50%）的模型被注入了触发器，导致当触发器存在时，对图像的分类产生误判。更正：在数据集打包过程中，以下模型受到污染，导致原本纯净的模型含有触发器。请避免使用这些模型。鉴于第五轮与第六轮数据集（均包含类似训练的情感分类AI模型）之间的相似性，数据集编制者建议忽略第五轮数据，仅使用第六轮数据。受污染模型：[id-00000000, id-00000019, id-00000033, id-00000084, id-00000087, id-00000104, id-00000146, id-00000148, id-00000167, id-00000212, id-00000221, id-00000230, id-00000233, id-00000237, id-00000239, id-00000246, id-00000281, id-00000284, id-00000288, id-00000295, id-00000302, id-00000303, id-00000310, id-00000343, id-00000349, id-00000351, id-00000361, id-00000366, id-00000367, id-00000369, id-00000371, id-00000376, id-00000407, id-00000418, id-00000423, id-00000425, id-00000428, id-00000439]