Effectiveness of dataset reduction in testing machine learning algorithms
Abstract Many machine learning algorithms examine large amounts of data to discover insights from hidden patterns. Testing these algorithms can be expensive and time-consuming. There is a need to speed up the testing process, especially in an agile
On Data Integrity Attacks against Industrial Internet of Things
Industrial Internet of Things (IIoT) is predicted to drive the fourth industrial revolution through massive interconnection of industrial devices, such as sensors, controllers and actuators, integrating advances in smart machinery and data analytics driven
During Fiscal Year 2019 (FY 2019), from October 1, 2018 through September 30, 2019, the NIST Information Technology Laboratory (ITL) Cybersecurity and Privacy Program successfully responded to numerous challenges and opportunities in security and privacy
Four Principles of Explainable Artificial Intelligence (Draft)
We introduce four principles for explainable artificial intelligence (AI) that comprise the fundamental properties for explainable AI systems. They were developed to encompass the multidisciplinary nature of explainable AI, including the fields of computer
ARES: Automated Risk Estimation in Smart Sensor Environments
Industry 4.0 adoption demands integrability, interoperability, composability, and security. Currently, integrability, interoperability and composability are addressed by next-generation approaches for enterprise systems integration such as model-based
Linking Performance Data and Geospatial Information of Manufacturing Assets through Standard Representations
Interoperability across emerging visualization modalities, including augmented reality (AR) and virtual reality (VR), remains a challenge with respect to industrial applications. One critical issue relates to the lack of standard approaches for
3D BUILD MELT POOL PREDICTIVE MODELING FOR POWDER BED FUSION ADDITIVE MANUFACTURING
Melt pool size is a critical intermediate measure that reflects the outcome of a laser powder bed fusion process setting. Reliable melt pool predictions prior to builds can help users to evaluate potential part defects such as lack of fusion and over
Zero trust (ZT) is the term for an evolving set of cybersecurity paradigms that move defenses from static, network- based perimeters to focus on users, assets, and resources. A zero trust architecture (ZTA) uses zero trust principles to plan industrial and
Uncertainty of Large-Signal Measurements Under Variable Load Conditions
We thoroughly investigate the uncertainty of large-signal measurements when load conditions at the fundamental frequency change. In particular, we evaluate uncertainties of the incident a2 and scattered b2 frequency-domain spectra. They are of particular
A Document-based View of the Risk Management Framework
Cybersecurity professionals know the Risk Management Framework as a rigorous yet flexible process for managing security risk. But the RMF lacks a document focus, even though much of the process requires authoring, reviewing, revising, and accessing plans
A timestamp is a critical component in many applications, such as proof of transaction ordering or analyzing algorithm performance. This paper reports on a method called Verified Timestamping (VT) that improves the standard timestamp protocol. VT was
A smart grid messaging framework is known as an Open Field Message Bus (OpenFMB, which was ratified by the North American Energy Standards Board (NAESB) in March 2016 and has been released as NAESB RMQ.26, Open Field Message Bus (OpenFMB) Model Business
NIST 2020 CTS Speaker Recognition Challenge Evaluation Plan
Following the success of the 2019 Conversational Telephone Speech (CTS) Speaker Recognition Challenge, which received 1347 submissions from 67 academic and industrial organizations, the US National Institute of Standards and Technology (NIST) will be
Systems security assurance as (micro) publishing: Declarative markup for systems description and assessment
Markup technologies are very general purpose, as reflects their generality of conception. They become interesting as well as useful as they are applied to accomplish goals in the real world. Since principles of generic declarative markup were first applied
The Deep Learning Track is a new track for TREC 2019, with the goal of studying ad hoc ranking in a large data regime. It is the first track with large human-labeled training sets, introducing two sets corresponding to two tasks, each with rigorous TREC