Data Publication
Trojan Detection Software Challenge - nlp-question-answering-aug2023-train
Michael Majurski 
, Timothy Blattner , Derek Juba
, Timothy Blattner , Derek Juba Contact: Michael Paul Majurski.
Version: 1.0... First Released: 2023-09-14 Revised: 2023-09-14
nlp-question-answering-aug2023-train
This is the train data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform extractive question answering 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.
Research Areas
NIST R&D: Information Technology: Software researchInformation Technology: Cybersecurity
Keywords: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;
- These data are public.
Data and related material can be found at the following locations:
Version: 1.0... First Released: 2023-09-14 Revised: 2023-09-14
Cite this dataset
Michael Majurski, Timothy Blattner, Derek Juba (2023), Trojan Detection Software Challenge - nlp-question-answering-aug2023-train, National Institute of Standards and Technology, https://doi.org/10.18434/mds2-3065 (Accessed 2025-05-23) Repository Metadata
Machine-readable descriptions of this dataset are available in the following formats: NERDm
Access Metrics
Metrics data is not available for all datasets, including this one. This may be because the data is served via servers external to this repository. 