Specimens from one build of laser powder bed fusion (PBF-L) titanium alloy (Ti-6Al-4V) were split equally into two heat treatment conditions. The first condition is a non-standard hot isostatic pressing (HIP) heat treatment (800 °C, 2 h, argon pressure of 200 MPa, approximately 12 °C/min cooling rate), which will be referred to as 800HIP. The second condition is the same heat treatment but in a vacuum furnace with a partial pressure of argon (75 mTorr), and will be referred to as 800VAC.

This challenge is a follow-on from AMB2022-01 laser powder bed fusion (PBF-LB) alloy Inconel 718 in the as-built condition (no heat treatment). Eight continuum-but-miniature tensile specimens were excised from the same size legs (2.5 mm width) of one original AMB2022-01 specimen (AMB2022-718-AMMT-B7-P4). Excised tensile specimens were quasi-static uniaxially tensile tested according to ASTM E8 (strain rate 1*10-3 sec-1, 3 mm gauge length custom contact extensometer).

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of RL agents operating in the Safety Gymnasium 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 that trigger behavior in the trained AI models.

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of instruction fine tuned LLMs. 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 mitigating that trigger behavior in the trained AI models.

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of instruction fine tuned LLMs. 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 that trigger behavior in the trained AI models.

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of models trained to predict whether code from public git repositories would survive in its branch for one month or more as a quantifiable proxy for code quality. 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 that trigger behavior in the trained AI models.

These sets of automated serial sectioning electron backscatter diffraction (EBSD) and X-ray computed tomography (XRCT) measurements were designed to produce spatially registered, multi-modal datasets within a region of interest (ROI) of an additive manufacturing benchmark test series (AM Bench) nickel alloy 718 specimen produced using laser powder bed fusion (PBF-LB) additive manufacturing (AM). The serial sectioning data are in the form of 2D slices which were reconstructed and registered to make 3D data sets that can be analyzed and visualized using open source software.

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of RL agents operating in the Colorful Memory 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 that trigger behavior in the trained AI models.

This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of malware packer classification AIs. 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 mitigating/removing that trigger behavior from the trained AI models.

mitigation-image-classification-jun2024-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. 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 mitigating/removing that trigger behavior from the trained AI models. This dataset consists of 288 AI models using a small set of model architectures.