Trojan Detection Software Challenge - image-classification-jun2020-holdout
Round1 Holdout DatasetThe data being generated and disseminated is the holdout data used to evaluate 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 1000 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.
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| bureauCode |
[
"006:55"
]
|
| contactPoint |
{
"fn": "Michael Paul Majurski",
"hasEmail": "mailto:michael.majurski@nist.gov"
}
|
| description | Round1 Holdout DatasetThe data being generated and disseminated is the holdout data used to evaluate 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 1000 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. |
| distribution |
[
{
"title": "image-classification-jun2020-holdout",
"accessURL": "https://drive.google.com/drive/folders/1o9GcpZJOA8UJVcUWJ5NStD77WCY7XSof?usp=drive_link"
}
]
|
| identifier | ark:/88434/mds2-2284 |
| issued | 2020-08-04 |
| keyword |
[
"Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;"
]
|
| landingPage | https://data.nist.gov/od/id/mds2-2284 |
| language |
[
"en"
]
|
| license | https://www.nist.gov/open/license |
| modified | 2020-07-28 00:00:00 |
| programCode |
[
"006:045"
]
|
| publisher |
{
"name": "National Institute of Standards and Technology",
"@type": "org:Organization"
}
|
| theme |
[
"Information Technology:Computational science",
"Information Technology:Cybersecurity",
"Information Technology:Software research"
]
|
| title | Trojan Detection Software Challenge - image-classification-jun2020-holdout |
