Round 2 Holdout DatasetThe data being generated and disseminated is the holdout data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform a variety of tasks (image classification, natural language processing, etc.). 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 3 Test DatasetThe data being generated and disseminated is the training data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform image classification. 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 3 Holdout DatasetThe data being generated and disseminated is the training data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform image classification. 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 4 Train DatasetThe data being generated and disseminated is the training data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform image classification. 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 4 Test DatasetThe data being generated and disseminated is the test data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform image classification. 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 4 Holdout DatasetThe data being generated and disseminated is the holdout data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform image classification. 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 5 Train DatasetThe data being generated and disseminated is the train data used to construct trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform text sentiment classification 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.

This Standard Reference Material (SRM) is intended for use as a primary calibration standard for the quantitative determination of aluminum. A unit of SRM 3101a consists of five 10 mL sealed borosilicate glass ampoules of an acidified aqueous solution prepared gravimetrically to contain a known mass fraction of aluminum. The solution contains nitric acid at a volume fraction of approximately 10 %, equivalent to an amount of substance concentration (molarity) of approximately 1.6 mol/L. This data is public in the Certificate of Analysis for this material.

This Standard Reference Material (SRM) is intended for use as a primary calibration standard for the quantitative determination of antimony. A unit of SRM 3102a consists of 50 mL of an acidified aqueous solution prepared gravimetrically to contain a known mass fraction of antimony in a high-density polyethylene bottle sealed in an aluminized bag.