Skip to main content
U.S. flag

An official website of the United States government

Skip to content

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

Metadata Updated: September 30, 2023

Round 6 Train DatasetThis 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 48 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.

Access & Use Information

Public: This dataset is intended for public access and use. License: See this page for license information.

Downloads & Resources

Dates

Metadata Created Date April 10, 2021
Metadata Updated Date September 30, 2023

Metadata Source

Harvested from NIST

Additional Metadata

Resource Type Dataset
Metadata Created Date April 10, 2021
Metadata Updated Date September 30, 2023
Publisher National Institute of Standards and Technology
Maintainer
Identifier ark:/88434/mds2-2386
Data First Published 2021-03-29
Language en
Data Last Modified 2021-03-26 00:00:00
Category Information Technology:Software research, Information Technology:Cybersecurity, Information Technology:Computational science
Public Access Level public
Bureau Code 006:55
Metadata Context https://project-open-data.cio.gov/v1.1/schema/data.json
Schema Version https://project-open-data.cio.gov/v1.1/schema
Catalog Describedby https://project-open-data.cio.gov/v1.1/schema/catalog.json
Harvest Object Id b7a1b49a-7f0d-48e6-80a7-2d5490626ffb
Harvest Source Id 74e175d9-66b3-4323-ac98-e2a90eeb93c0
Harvest Source Title NIST
Homepage URL https://data.nist.gov/od/id/mds2-2386
License https://www.nist.gov/open/license
Program Code 006:045
Source Datajson Identifier True
Source Hash 859305851c9f4362afe54dfbe1b2980c4a0e2fff07f0dde856554fe84523d983
Source Schema Version 1.1

Didn't find what you're looking for? Suggest a dataset here.