Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “trustworthiness”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

EXPLAINABLE AND TRUSTWORTHY DIAGNOSTICS ACHIEVABLE THROUGH PROCESS-BASED AUTOMATED REASONING

An approach has been developed that incorporates domain knowledge to obtain a more explainable and trustworthy equipment health monitoring diagnosis than might otherwise be obtained from a purely data-driven method. Physics-based models serve to constrain the realizable solution space and render a more trusted diagnosis. An automated reasoning algorithm performs backward chaining to infer a diagnosis that is consistent with logic statements that have been evaluated as true. This diagnosis is made explainable to an operator by providing the forward chaining path that elucidates for inspection and validity testing those truths implied by the diagnosis.

automated reasoning↗

Computational Models of Trustworthiness and Trust in Autonomous Cyber-Physical-Human Systems

In this paper, we propose an approach to developing a concept of actionable trust in multi-agent,cyber-physical-human systems in safety-critical and time-critical environment of air transportation. Actionable trust requires computational models of trustworthiness and trust, for use during system design and in real time, during operations. We describe the models, examine their computability and scalability, as well as what remains to be done.

Autonomous Systems↗

Trustworthiness and Trust: Identifying Factors that Drive Successful Human-AI Interaction in Nuclear Power Plant Applications

Emerging technologies such as artificial intelligence (AI) and machine learning (ML) are rapidly evolving and considered a promising tool for efficient and continued safe operations of the U.S. nuclear power plants (NPPs). Emerging AI techniques like large language models (LLMs) are one such technology that may support personnel at existing NPPs perform work more efficiently. For example, operators may query the current operational status of a power plant via a chat interface leveraging LLMs to access plant-related information in an interactive manner rather than manually collecting various sensor data for tasks such as surveillances or completing work orders. This is a fundamental shift in the way operators currently perform their tasks today. The literature of human-automation interaction indicates that trust is a crucial factor that drives successful interaction between a human operator and an automated system, like an AI-infused NPP application. This work presents the results of a literature review on key factors that relate to trust in AI/LLM technologies for NPP applications. The relevant literature of human factors and cognitive engineering has identified various factors related to trust including trustworthiness, performance characteristics, operator skill and perceived risk. This preliminary literature review will guide development and evaluation of models involving the identified factors influencing trust in AI and develop a framework for human-centered design for interface between humans and AI. By addressing trust, this work supports developing a technical basis for designing key characteristics of AI/LLM to support calibrated trust, which will ultimately support wide-scale adoption of AI/LLM technologies, as well as ensure safe, effective, and reliable use.

99 - GENERAL AND MISCELLANEOUS↗

Scalable training of trustworthy and energy-efficient predictive graph foundation models for atomistic materials modeling: a case study with HydraGNN

We present our work on developing and training scalable, trustworthy, and energy-efficient predictive graph foundation models (GFMs) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) computations in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define nearest-neighbor convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFMs training to tens of thousands of GPUs on datasets consisting of hundreds of millions of graphs. Our GFMs use multitask learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as energy and atomic forces. Using over 154 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two state-of-the-art US Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge Leadership Computing Facility. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2000 GPUs on Perlmutter and 16,000 GPUs on Frontier.

97 MATHEMATICS AND COMPUTING↗

Trustworthiness of detectors in quantum key distribution with untrusted detectors

Measurement-device-independent quantum key distribution (MDI-QKD) protocol has been demonstrated as a viable solution to detector side-channel attacks. One of the main advantages of MDI-QKD is that the security can be proved without making any assumptions about how the measurement device works. The price to pay is the relatively low secure key rate comparing with conventional quantum key distribution (QKD), such as the decoy-state BB84 protocol. Recently a new QKD protocol, aiming at bridging the strong security of MDI-QKD with the high e ciency of conventional QKD, has been proposed. In this protocol, the legitimate receiver employs a trusted linear optics network to encode information on photons received from an insecure quantum channel, and then performs a Bell state measurement (BSM) using untrusted detectors. One crucial assumption made in most of these studies is that the untrusted BSM located inside the receiver's laboratory cannot send any unwanted information to the outside. Here in this paper, we show that if the BSM is completely untrusted, a simple scheme would allow the BSM to send information to the outside. Combined with Trojan horse attacks, this scheme could allow Eve to gain information of the quantum key without being detected. Ultimately, to prevent the above attack, either countermeasures to Trojan horse attacks or some trustworthiness to the "untrusted" BSM device is required.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Improving Trustworthiness of Data-Driven Power Grid Contingency Analysis With Bayesian Residual Graph Neural Networks

The evolving energy landscape requires novel tools to efficiently perform contingency analysis and reliability assessment of power grids, potentially in real-time. The high computational cost of traditional power flow solvers limits their applicability in practice. Machine learning (ML) surrogates such as deep neural networks (NNs) accelerate power flow solvers computations, enabling high-order contingency analysis and real-time decision-making by learning highly nonlinear functions and integrating grid topology via graph architectures. However, (graph) NNs lack predictive power away from training data and do not provide predictive confidence estimates. Here, we present a Bayesian residual graph NN that integrates knowledge from low-fidelity data via residual training and embeds granular quantification of uncertainties, improving trustworthiness critical for high-consequence decision-making. Applying Bayesian concepts to NNs is challenging due to the high-dimensionality of both the parameter space, complicating derivation of a meaningful prior, and the output space in large grid systems, requiring enhanced techniques to assess the predicted high-dimensional uncertainties. Our contributions include: (1) Deriving a prior for fully connected and graph NNs that leverages low-fidelity data to guide mean predictions and appropriately control prior predictive uncertainty. (2) Integrating this prior within an ensembling with anchoring scheme for efficient approximate posterior inference. (3) Deriving enhanced metrics to assess accuracy of both the mean and uncertainty predictions in high dimensions, appropriately accounting for correlations propagated through graph layers. The resulting Bayesian residual graph NN is tested on a contingency analysis task for 14-bus and 118-bus grids.

24 - POWER TRANSMISSION AND DISTRIBUTION↗

Explainable and trustworthy artificial intelligence for correctable modeling in chemical sciences

Data science has primarily focused on big data, but for many physics, chemistry, and engineering applications, data are often small, correlated and, thus, low dimensional, and sourced from both computations and experiments with various levels of noise. Typical statistics and machine learning methods do not work for these cases. Expert knowledge is essential, but a systematic framework for incorporating it into physics-based models under uncertainty is lacking. Here, we develop a mathematical and computational framework for probabilistic artificial intelligence (AI)–based predictive modeling combining data, expert knowledge, multiscale models, and information theory through uncertainty quantification and probabilistic graphical models (PGMs). We apply PGMs to chemistry specifically and develop predictive guarantees for PGMs generally. Our proposed framework, combining AI and uncertainty quantification, provides explainable results leading to correctable and, eventually, trustworthy models. The proposed framework is demonstrated on a microkinetic model of the oxygen reduction reaction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

ChatHPC: Building the Foundations for a Productive and Trustworthy AI-Assisted HPC Ecosystem

ChatHPC democratizes large language models for the high-performance computing (HPC) community by providing the infrastructure, ecosystem, and knowledge needed to apply modern generative AI technologies to rapidly create specific capabilities for critical HPC components while using relatively modest computational resources. Our divide-and-conquer approach focuses on creating a collection of reliable, highly specialized, and optimized AI assistants for HPC based on the cost-effective and fast Code Llama fine-tuning processes and expert supervision. We target major components of the HPC software stack, including programming models, runtimes, I/O, tooling, and math libraries. Thanks to AI, ChatHPC provides a more productive HPC ecosystem by boosting important tasks related to portability, parallelization, optimization, scalability, and instrumentation, among others. With relatively small datasets (on the order of KB), the AI assistants, which are created in a few minutes by using one node with two NVIDIA H100 GPUs and the ChatHPC library, can create new capabilities with Meta’s 7-billion parameter Code Llama base model to produce high-quality software with a level of trustworthiness of up to 90% higher than the 1.8-trillion parameter OpenAI ChatGPT-4o model for critical programming tasks in the HPC software stack.

Young, Aaron [ORNL] (ORCID:0000000254484667)↗

Trustworthy Cyber Infrastructure for the Power Grid (TCIPG) Final Technical Report - November 20, 2015

The Trustworthy Cyber Infrastructure for the Power Grid project (TCIPG) was funded by DOE and DHS for a period of performance that ran from October 1, 2009 to August 31 2015. The partnership included the University of Illinois at Urbana-Champaign (lead institution) and partner institutions Arizona State University (replacing original partner UC Davis when faculty moved), Dartmouth College, and Washington State University. TCIPG was a unique public-private partnership of government, academia, and industry that was formed to meet the challenge of keeping our power grid secure. TCIPG followed from the earlier NSF-funded TCIP project, which kicked off in 2005. At that time, awareness of cyber security and resiliency in grid systems (and in control systems in general) was low, and the term “smart grid” was not in wide use. The original partnership was formed from a team of academic researchers with a shared vision for the importance of research in this area, and a commitment to producing more impactful results through early involvement of industry. From the TCIPG standpoint, “industry” meant both utilities (investor-owned as well as cooperatives and municipals) and system vendors (who sell technology to the utility sector). Although TCIPG was a university-led initiative, we have from the start stressed real-world impact and partnership with industry. That has led to real-world adoption of TCIPG technologies within the industry, achieving practical benefits. This report summarizes the achievements of TCIPG over its period of performance.

97 MATHEMATICS AND COMPUTING↗

Applied Resiliency for More Trustworthy Grid Operation (ARMORE) (Final Technical Report)

Applied Resiliency for More Trustworthy Grid Operation (ARMORE) is an open-source software system that can perform inspection of network packets and alarm on communication that does not comply with the specified ARMORE policy. ARMORE can be configured to take action to block network traffic based on deep inspection of common substation communications protocols, such as the Distributed Network Protocol (DNP3). After validation for compliance with policy, ARMORE can encapsulate and encrypt legacy communications and resiliently transmit this information among ARMORE nodes (such as between the substation and the control center). Through this peer-based framework for secure information exchange, ARMORE provides the functionality to push secure, fault-tolerant real-time communication capabilities deeper into critical utility networks

24 POWER TRANSMISSION AND DISTRIBUTION↗

Towards Trustworthy and Interpretable Deep Learning-assisted Ecohydrological Models

The transformational science question we plan to address is: How do we leverage in-situ observations and simulations from process-based ecohydrological model to construct interpretable and trustworthy deep learning (DL) models for improved reliability of prediction of quantities of interest (QoIs) under hydro-climatic extremes?

54 ENVIRONMENTAL SCIENCES↗

Trustworthy AI for Extreme Event Prediction and Understanding

Our transformational science question is: can we revolutionize both the prediction and understanding of extreme events through trustworthy AI? Our use-cases include extreme weather such as tornadoes and hail as well as water-based events including extreme precipitation, compound flooding, harmful algal blooms, and sea turtle cold stunnings and nest inundations.

54 ENVIRONMENTAL SCIENCES↗

Traveler Trustworthy Autonomy

NASAs Armstrong Flight Research Center has been engaged in the development of highly automatic safety systems for aviation since the mid 80s. For the past three years under Seedling and Center Innovation funding this work has moved toward the development of a software architecture applicable to autonomous safety. This work is now broadening and accelerating to address the airworthiness issues surrounding making a case for trustworthy autonomy. This software architecture is called the expandable variable-autonomy architecture (EVAA) and utilizes a run-time assurance approach to safety assurance.

autonomy↗

The Trustworthy Digital Camera: Restoring Credibility to the Photographic Image

The increasing sophistication of computers has made digital manipulation of photographic images incredibly easy to perform and, as time goes on, increasingly difficult to detect. The proposed device is a new type of digital camera whose output can be certified as being unretouched, and can restore the credibility that the photographic image once enjoyed. The Trustworthy Digital Camera employs public key encryption techniques at the system level, and produces an encrypted digital signature and a standard-format digital image file each time a picture is taken. Although digitally retouching or altering these image files would still be possible, doing so will cause a mismatch with the verifying signature, proving that the image is not an untouched original...

Friedman, Gary L.↗

Making Dataset Quality Information FAIR: Supporting Open-Source Science and Enhancing (Re)Use and Trustworthiness of Scientific Data

- Quality information should be documented and readily shared within and across domains. - Sharing of dataset quality information supports open science and trustworthiness of scientific data. - Dataset quality is more than data quality. - Quality tends to be domain-specific and context-dependent. - Community guidelines provide practical steps towards FAIR dataset quality information.

Ge Peng↗

Trustworthy Autonomy for Gateway Vehicle System Manager

This webinar will present techniques for achieving trusted autonomous operations that are being pioneered on the NASA Lunar Gateway Vehicle System Manager (VSM). The challenges of achieving trusted autonomy faced by the VSM project are similar to challenges in underwater autonomous systems. The webinar will describe the overall approach to verification and present in detail the use of design-time (development) assume-guarantee contracts using model checking and runtime (operational) assume-guarantee contracts. The webinar will conclude with a summary of lessons learned to date and future challenges.

Assume-guarantee contracts↗