Trojan Detection Software Challenge - mitigation-llm-instruct-oct2024-train
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.
Resources
| Name |
Format |
Description |
Link |
|
0 |
|
https://drive.google.com/drive/folders/1evPD-gD3doNtUH5JTSEwCTz_lGzuus8g?usp=sharing |
Tags
- trojan-detection-artificial-intelligence-ai-machine-learning-adversarial-machine-learning