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.
About this Dataset
| Title | Challenge Round 0 (Dry Run) Test Dataset |
|---|---|
| Description | 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. |
| Modified | 2020-02-04 00:00:00 |
| Publisher Name | National Institute of Standards and Technology |
| Contact | mailto:[email protected] |
| Keywords | Trojan Detection , Artificial Intelligence , AI , Machine Learning , Adversarial Machine Learning |
{
"identifier": "ark:\/88434\/mds2-2175",
"accessLevel": "public",
"contactPoint": {
"hasEmail": "mailto:[email protected]",
"fn": "Michael Paul Majurski"
},
"programCode": [
"006:045"
],
"@type": "dcat:Dataset",
"landingPage": "https:\/\/data.nist.gov\/od\/id\/mds2-2175",
"description": "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.",
"language": [
"en"
],
"title": "Challenge Round 0 (Dry Run) Test Dataset",
"distribution": [
{
"downloadURL": "https:\/\/data.nist.gov\/od\/ds\/ark:\/88434\/mds2-2175\/trojai-round0-dataset.tar.gz",
"mediaType": "application\/gzip"
},
{
"downloadURL": "https:\/\/data.nist.gov\/od\/ds\/ark:\/88434\/mds2-2175\/trojai-round0-dataset.tar.gz.sha256",
"mediaType": "text\/plain"
},
{
"accessURL": "https:\/\/doi.org\/10.18434\/M32175",
"title": "DOI Access for Challenge Round 0 (Dry Run) Test Dataset"
}
],
"license": "https:\/\/www.nist.gov\/open\/license",
"bureauCode": [
"006:55"
],
"modified": "2020-02-04 00:00:00",
"publisher": {
"@type": "org:Organization",
"name": "National Institute of Standards and Technology"
},
"accrualPeriodicity": "irregular",
"theme": [
"Information Technology:Computational science",
"Information Technology:Software research"
],
"issued": "2020-02-07",
"keyword": [
"Trojan Detection",
"Artificial Intelligence",
"AI",
"Machine Learning",
"Adversarial Machine Learning"
]
}
