Public Data Resource

Challenge Round 0 (Dry Run) Test Dataset

Contact: Michael Paul Majurski.
Identifier: doi:10.18434/M32175
Version: 1.2... Revised: 2021-11-09
This dataset was an initial test harness infrastructure test for the TrojAI program. It should not be used for research. Please use the more refined datasets generated for the other rounds. The data being generated and disseminated is training, validation, and test data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform a variety of tasks (image classification, natural language processing, etc.). 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 200 trained, human level, image classification AI models using the following architectures (Inception-v3, DenseNet-121, and ResNet50). The models were trained on synthetically created image data of non-real traffic signs superimposed on road background scenes. Half (50%) of the models have been poisoned with an embedded trigger which causes misclassification of the images when the trigger is present.
Research Areas
NIST R&D: Information Technology: Computational scienceInformation Technology: Software research
Keywords: Trojan DetectionArtificial IntelligenceAIMachine LearningAdversarial Machine Learning
These data are public.
Files

Loading file list...

Version: 1.2... Revised: 2021-11-09
Cite this dataset
Michael Paul Majurski (2020), Challenge Round 0 (Dry Run) Test Dataset, National Institute of Standards and Technology, https://doi.org/10.18434/M32175 (Accessed 2025-02-14)
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.