Software

Minimal TrojAI Example

NIST has developed and released a minimal working example showing a submission to the TrojAI NIST Test and Evaluation server. This ‘solution’ loads the model file, inferences 10 random tensors, and then writes a random number to the output file.

https://github.com/usnistgov/trojai-example

Included in the repository README.md is instructions for:

1. confirming the code works on your hardware, and

2. packaging the solution into a Singularity container.

Trojan Embedding Tools

The tools NIST used to embed trojans into models were created at JHU/APL.

A portion of this toolkit has been publicly released, allowing you to create your own set of trojaned or clean AIs.

• Trojan Toolkit

• Toolkit Documentation

Google Drive API Tools

NIST has developed and released a setup of Python based Google Drive API tools to programmatically interacting with a Google Drive Account.

https://github.com/usnistgov/gdrive-file-io-utility

Included in the repository README.md is instructions for:

1. Enabling Google Drive API access

2. Creating OAuth tokens

3. Configuring your Python virtual environment to install the dependencies

Round Generation Code

The NIST codebase for creating the datasets underlying each round of the TrojAI competition is available on GitHub. Each round’s data generation codebase is released after the round closes.

https://github.com/usnistgov/trojai-round-generation

Each round’s generation code is included as a branch in this repository, with the branch named after the round.