Return to search results
Trojan Detection Software Challenge - mitigation-llm-instruct-oct2024-train
This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of instruction fine tuned LLMs. 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 mitigating that trigger behavior in the trained AI models.
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| bureauCode |
[
"006:55"
]
|
| contactPoint |
{
"fn": "Michael Paul Majurski",
"hasEmail": "mailto:michael.majurski@nist.gov"
}
|
| description | This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of instruction fine tuned LLMs. 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 mitigating that trigger behavior in the trained AI models. |
| distribution |
[
{
"title": "llm-instruct-oct2024-train",
"accessURL": "https://drive.google.com/drive/folders/1evPD-gD3doNtUH5JTSEwCTz_lGzuus8g?usp=sharing"
}
]
|
| identifier | ark:/88434/mds2-3657 |
| issued | 2024-12-18 |
| keyword |
[
"Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;"
]
|
| landingPage | https://data.nist.gov/od/id/mds2-3657 |
| language |
[
"en"
]
|
| license | https://www.nist.gov/open/license |
| modified | 2024-10-30 00:00:00 |
| programCode |
[
"006:045"
]
|
| publisher |
{
"name": "National Institute of Standards and Technology",
"@type": "org:Organization"
}
|
| theme |
[
"Information Technology:Cybersecurity",
"Information Technology:Software research"
]
|
| title | Trojan Detection Software Challenge - mitigation-llm-instruct-oct2024-train |
