Trojan Detection Software Challenge - nlp-sentiment-classification-apr2021-train part2

Published by National Institute of Standards and Technology | National Institute of Standards and Technology | Metadata Last Checked: August 02, 2025 | Last Modified: 2021-03-22 00:00:00

Round 6 Train Dataset part2This is the training 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 96 sentiment classification AI models using a small set of model architectures. The models were trained on text data drawn from product reviews. Half (50%) of the models have been poisoned with an embedded trigger which causes misclassification of the input when the trigger is present.

Find Related Datasets

Click any tag below to search for similar datasets

Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;

Complete Metadata

bureauCode	[ "006:55" ]
identifier	ark:/88434/mds2-2405
issued	2021-05-14
landingPage	https://data.nist.gov/od/id/mds2-2405
language	[ "en" ]
programCode	[ "006:045" ]
theme	[ "Information Technology:Cybersecurity", "Information Technology:Software research" ]