Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Skip to content
  • Feedback

    • Trojan Detection Software Challenge - llm-pretrain-apr2024-train

    Metadata Updated: March 14, 2025

    TrojAI llm-pretrain-apr2024 Train DatasetThis is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists Llama2 Large Language Models refined using fine-tuning and LoRA to perform next token prediction. A known percentage of these trained AI models have been poisoned with triggers which induces modified behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers into the model weights.

    Access & Use Information

    Public: This dataset is intended for public access and use. License: See this page for license information.

    Downloads & Resources

    Dates

    Metadata Created Date May 15, 2024
    Metadata Updated Date March 14, 2025

    Metadata Source

    Harvested from NIST

    Other Data Resources

    Additional Metadata

    Resource Type Dataset
    Metadata Created Date May 15, 2024
    Metadata Updated Date March 14, 2025
    Publisher National Institute of Standards and Technology
    Maintainer
    Identifier ark:/88434/mds2-3235
    Data First Published 2024-04-19
    Language en
    Data Last Modified 2024-04-16 00:00:00
    Category Information Technology:Software research, Information Technology:Cybersecurity
    Public Access Level public
    Bureau Code 006:55
    Metadata Context https://project-open-data.cio.gov/v1.1/schema/data.json
    Schema Version https://project-open-data.cio.gov/v1.1/schema
    Catalog Describedby https://project-open-data.cio.gov/v1.1/schema/catalog.json
    Harvest Object Id 54f98099-de0c-4c7e-aa09-e5ac82e68da6
    Harvest Source Id 74e175d9-66b3-4323-ac98-e2a90eeb93c0
    Harvest Source Title NIST
    Homepage URL https://data.nist.gov/od/id/mds2-3235
    License https://www.nist.gov/open/license
    Program Code 006:045
    Source Datajson Identifier True
    Source Hash 3348826177615981006b863a218a53e2c5b6e8084ee5058c9f657352d146330b
    Source Schema Version 1.1

    Didn't find what you're looking for? Suggest a dataset here.