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.

Home to NTIA data and analysis on computer and Internet use in the United States. Since November 1994, NTIA has periodically sponsored data collections on Internet use and the devices Americans use to go online as a supplement to the Census Bureau’s annual Current Population Survey (CPS); analyzed the data; and reported the findings. In recent years, NTIA has also linked to the raw datasets on the Census Bureau website.