U.S. flag

An official website of the United States government

Dot gov

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Https

Secure .gov websites use HTTPS
A lock () or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Breadcrumb

  1. Home

Dataset Search

Search results

49 results found

Trojan Detection Software Challenge - image-classification-sep2022-train

Data provided by  National Institute of Standards and Technology

Round 11 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 trained on synthetic image data build from Cityscapes. 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 288 AI models using a small set of model architectures.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Trojan Detection Software Challenge - object-detection-feb2023-train

Data provided by  National Institute of Standards and Technology

Round 13 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 both on synthetic image data build from Cityscapes and the DOTA_v2 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 128 AI models using a small set of model architectures.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Trojan Detection Software Challenge - cyber-pdf-dec2022-train

Data provided by  National Institute of Standards and Technology

Round 12 Train DatasetThis is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of pdf malware classification AIs trained Contaigio dataset feature vectors. 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 120 AI models using a small set of model architectures.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Trojan Detection Software Challenge - nlp-summary-jan2022-test

Data provided by  National Institute of Standards and Technology

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.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Trojan Detection Software Challenge - nlp-summary-jan2022-holdout

Data provided by  National Institute of Standards and Technology

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.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Trojan Detection Software Challenge - object-detection-jul2022-train

Data provided by  National Institute of Standards and Technology

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.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Trojan Detection Software Challenge - rl-lavaworld-jul2023-train

Data provided by  National Institute of Standards and Technology

Round rl-lavaworld-jul2023-train Train DatasetThis is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of Reinforcement Learning agents trained to navigate the Lavaworld Minigrid 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 which trained AI models have been poisoned via embedded triggers.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Trojan Detection Software Challenge - nlp-question-answering-aug2023-train

Data provided by  National Institute of Standards and Technology

nlp-question-answering-aug2023-trainThis is the train data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform 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.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Trojan Detection Software Challenge - rl-randomized-lavaworld-aug2023-train

Data provided by  National Institute of Standards and Technology

Round rl-randomized-lavaworld-aug2023-train Train DatasetThis is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of Reinforcement Learning agents trained to navigate the Lavaworld Minigrid 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 which trained AI models have been poisoned via embedded triggers.

Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,

Modified: 2024-02-22

Views: 0

Dynamic compressive stress-strain curves of aluminum alloy 6061-T6 with rapid heating

Data provided by  National Institute of Standards and Technology

This dataset contains raw mechanical data (strain, stress and strain rate curvesand initial temperatures) for compression experiments performed on aluminum alloy 6061-T6using the NIST pulse-heated Kolsky Bar at strain rates between 2400 1/s and 2700 1/s and initialtemperatures from 23 °C to 527 °C and heating times ranging between 0.2 s and 3.5 s. At this time,the thermal history of the specimen during heating is not included in the dataset but this informationmay be included in a future update.

Tags: metals,mechanical properties,high heating rate,High Strain Rate,experiments,simulations,modeling,advanced manufacturing,machining,

Modified: 2024-02-22

Views: 0