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.

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.

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.

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.

Round 7 Test DatasetThis is the test 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 5 Test DatasetThis is the test 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 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.

Round 5 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 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.

Round 6 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 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.