Round 10 Train DatasetThis is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of object detection AIs trained on the COCO dataset. 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 which trained AI models have been poisoned via embedded triggers. This dataset consists of 144 AI models using a small set of model architectures.

Source code associated with the Inverted Library Search Algorithm (ILSA) for identifying mixture components using is-CID mass spectra. This source code is frozen to accompany the manuscript titled "Updates to the Inverted Library Search Algorithm for mixture analysis" by Moorthy et. al.

Round 9 Test DatasetThis is the test data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform one of three tasks, sentiment classification, named entity recognition, or extractive question answering on English text. 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 which trained AI models have been poisoned via embedded triggers.

Round 9 Holdout DatasetThis is the holdout data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform one of three tasks, sentiment classification, named entity recognition, or extractive question answering on English text. 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 which trained AI models have been poisoned via embedded triggers.

These LC-MS and LC-MS/MS raw data were collected for purposes of an interlaboratory study evaluating the multi-attribute method (MAM). Tryptic digests of native NISTmAb (the "Reference" and the "Unknown" samples), degraded NISTmAb (the "pH Stress" sample) and NISTmAb spiked with 15 heavy-labeled synthetic peptides (the "Spike" sample) were sent to each participating laboratory. One injection of each digest was acquired in MS-only mode, while a second injection was acquired in MS/MS mode.

Round 8 Train DatasetThis is the training data used to construct and evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform extractive question answering (QA on English text. 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 which trained AI models have been poisoned via embedded triggers.

SRM 2969 Electronic files containing certified values and their uncertainties, and the data used to assign those values

Electronic files containing certified values and their uncertainties, and the data used to assign those values.

Round 7 Holdout DatasetThis is the holdout data used to construct and evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform named entity recognition (NER) on English text. 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 which trained AI models have been poisoned via embedded triggers.

Round 7 Train DatasetThis is the training data used to construct and evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform named entity recognition (NER) on English text. 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 which trained AI models have been poisoned via embedded triggers.