Dataset Search
Sort By
Search results
96 results found
Trojan Detection Software Challenge - image-classification-aug2020-holdout
Data provided by National Institute of Standards and Technology
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.
Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,
Modified: 2024-02-22
Views: 0
Trojan Detection Software Challenge - image-classification-dec2020-test
Data provided by National Institute of Standards and Technology
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.
Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,
Modified: 2024-02-22
Views: 0
Trojan Detection Software Challenge - image-classification-dec2020-holdout
Data provided by National Institute of Standards and Technology
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.
Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,
Modified: 2024-02-22
Views: 0
Trojan Detection Software Challenge - image-classification-feb2021-train
Data provided by National Institute of Standards and Technology
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.
Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,
Modified: 2024-02-22
Views: 0
Trojan Detection Software Challenge - image-classification-feb2021-test
Data provided by National Institute of Standards and Technology
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.
Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,
Modified: 2024-02-22
Views: 0
Trojan Detection Software Challenge - image-classification-feb2021-holdout
Data provided by National Institute of Standards and Technology
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.
Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,
Modified: 2024-02-22
Views: 0
Trojan Detection Software Challenge - nlp-sentiment-classification-mar2021-train
Data provided by National Institute of Standards and Technology
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.
Tags: Trojan Detection; Artificial Intelligence; AI; Machine Learning; Adversarial Machine Learning;,
Modified: 2024-02-22
Views: 0
NIST MEMS Calculator - SRD 166
Data provided by National Institute of Standards and Technology
This MEMS Calculator determines the following thin film properties from data taken with an optical interferometer or comparable instrument: a) residual strain from fixed-fixed beams, b) strain gradient from cantilevers, c) step heights or thicknesses from step-height test structures, and d) in-plane lengths or deflections. Then, residual stress and stress gradient calculations can be made after an optical vibrometer or comparable instrument is used to obtain Young's modulus from resonating cantilevers or fixed-fixed beams.
Tags: ASTM,MEMS 5 in 1,MEMS Calculators,Micro Electro Mechanical Systems,Semiconductor Equipment and Materials International,Standard Reference Material,Young's modulus measurements,cantilevers,data analysis sheets,fixed-fixed beams,height measurements,interferometries,length measurements,residual strains,residual stresses,steps,strain gradients,stress gradients,test structures,thick,vibrometries,
Modified: 2024-02-22
Views: 0
SRM 131h Refined Cast Iron
Data provided by National Institute of Standards and Technology
Standard Reference Material 131h Refined Cast Iron - This Standard Reference Material (SRM) is intended primarily for use in validation of chemical and instrumental methods of analysis. It can be used to validate value assignment of in-house reference materials and, if necessary, to calibrate carbon/sulfur analyzers. A unit of SRM 131h consists of a bottle containing 100 g of chips. This data is public in the Certificate of Analysis for this material.
Tags: low alloy steel,cast iron,carbon,sulfur,Standard Reference Material,SRM,SRM 131h,combustion,infrared detection,manufacturing specification,manufacturing,
Modified: 2024-02-22
Views: 0
SRM 1632d Trace Elements in Coal (Bituminous)
Data provided by National Institute of Standards and Technology
Standard Reference Material 1632d Trace Elements in Coal (Bituminous) - This Standard Reference Material (SRM) is intended primarily for use in the evaluation of techniques used in the analysis of coals and materials of a similar matrix. A unit of SRM 1632d consists of 50 g of bituminous coal that was ground to pass a 250 µm (60 mesh) sieve, homogenized, bottled under an argon atmosphere, and sealed in an aluminized bag. This data is public in the Certificate of Analysis for this material.
Tags: SRM,Standard Reference Material,coal,sulfur,mercury,chlorine,trace elements,Energy,
Modified: 2024-02-22
Views: 0