This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of RL agents operating in the Safety Gymnasium environment. 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 that trigger behavior in the trained AI models.

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.

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 detecting that trigger behavior in the trained AI models.

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of models trained to predict whether code from public git repositories would survive in its branch for one month or more as a quantifiable proxy for code quality. 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 that trigger behavior in the trained AI models.

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of RL agents operating in the Colorful Memory environment. 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 that trigger behavior in the trained AI models.

To bridge the gap between the development of greenhouse gas (GHG) and air quality (AQ) emission inventories, we developed the GReenhouse gas And Air Pollutant Emissions System (GRA2PES), which provides self-consistent GHG and AQ emissions over the contiguous U.S. This inventory provides emissions at 4 km x 4 km spatial resolution with year, month, day-of-week, and diurnal temporal information. GRA2PES utilizes datasets from the U.S. Energy Information Administration (EIA) and the U.S.

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of malware packer classification AIs. 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/removing that trigger behavior from the trained AI models.

mitigation-image-classification-jun2024-train datasetThis is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of image classification AIs. 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/removing that trigger behavior from the trained AI models. This dataset consists of 288 AI models using a small set of model architectures.

Open-path near-IR dual-comb spectra collected at Mauna Loa Observatory in spring 2021, fit with different absorption models (eg HITRAN) and compared against NOAA GML's record.

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.