Search NASA⌕ Search

Engineering topics

Martindale, Nathan

Publications and source records attributed to Martindale, Nathan.

15 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

AI for Nuclear Safeguards Verification

The International Atomic Energy Agency (IAEA) utilizes AI/ML to analyze open-source information, including satellite imagery and scientific publications, to verify the completeness of State declarations regarding nuclear activities. AI/ML already assist the IAEA with automating processes and analysis of large datasets, including satellite imagery and unstructured data, improving efficiency and effectiveness of safeguards implementation. AI/ML in nuclear safeguards come with its own challenges that include the need for large, unbiased datasets, the risk of AI-generated fake information, including the potential for manipulation of satellite imagery.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Supporting Greater Interactivity in the IPython Visualization Ecosystem

Interactive visualizations are invaluable tools for building intuition and supporting rapid exploration of datasets and models. Numerous libraries in Python support interactivity, and workflows that combine Jupyter and IPyWidgets in particular make it straightforward to build data analysis tools on the fly. However, the field is missing the ability to arbitrarily overlay widgets and plots on top of others to support more flexible details-on-demand techniques. This work discusses some limitations of the base IPyWidgets library, explains the benefits of IPyVuetify and how it addresses these limitations, and finally presents a new open-source solution that builds on IPyVuetify to provide easily integrated widget overlays in Jupyter.

Martindale, Nathan↗
DOE OSTI2023

Curifactory: A research experiment manager

Curifactory is a command line tool and framework for organizing Python experiment code, configuration parameters, and results. It is an opinionated and lightweight approach to workflow management infrastructure and is primarily intended to support researchers conducting experiments on one machine. This software was developed to support the reproducibility of results for several data science projects in the Nuclear Nonproliferation Division at Oak Ridge National Laboratory. Curifactory is intended to be a general framework and is not specific to machine learning or data science. It can aid in any field in which experiments are primarily computation-based studies and can be implemented in Python (e.g., high-energy physics, astronomy, computational chemistry). Here, the design emphasizes the automated caching of intermediate data analysis artifacts to speed up development involving computationally intensive tasks. It also allows for data provenance and experiment reproduction. Individual experiment runs are tracked through logs and their output reports, and entire copies of a run with all cached data and metadata can be exported for others to run using Curifactory on another machine. Curifactory experiments can either be integrated into a project from the beginning or can be written on top of an existing codebase without needing significant modification. A few important views of the Curifactory library can be seen in Figure 1.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

TX$^2$: Transformer eXplainability and eXploration

The Transformer eXplainability and eXploration (Martindale & Stewart, 2021), or TX 2 software package, is a library designed for artificial intelligence researchers to better understand the performance of transformer models (Vaswani et al., 2017) used for sequence classification. The tool is capable of integrating with a trained transformer model and a dataset split into training and testing populations to produce an ipywidget (Project Jupyter Contributors, 2021) dashboard with a number of visualizations to understand model performance with an emphasis on explainability and interpretability. The TX 2 package is primarily intended to integrate into a workflow centered around Jupyter Notebooks (Kluyver et al., 2016), and currently assumes the use of PyTorch (Paszke et al., 2019) and Hugging Face transformers library (Wolf et al., 2020). The dashboard includes visualization and data exploration features to aid researchers, including an interactive UMAP embedding graph (McInnes et al., 2018) to understand classification clusters, a word salience map that can be updated as researchers alter textual entries in near real time, a set of tools to understand word frequency and importance based on the clusters in the UMAP embedding graph, and a set of traditional confusion matrix analysis tools.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Enabling Computation on Sensitive Data in International Safeguards with Privacy-Preserving Encryption Techniques

Privacy-preserving machine learning is a field of study that explores how to protect and preserve the privacy of sensitive data while allowing the data to be used by machine learning algorithms. This field has had substantial industry investment due to heightened concerns about privacy in the technology industry, with a focus in two broad application areas: financial services and healthcare. Numerous privacy-preserving methods have also been proposed for international safeguards, but they have been difficult to enact because the data they require is con- sidered sensitive or proprietary by the nuclear facility operator. This work examines how current privacy-preserving approaches might be used to enable the International Atomic Energy Agency (IAEA) to use that data to contribute to a safeguards conclusion about a state while giving nuclear operators confidence that their sensitive data is adequately protected. This paper begins by exploring several broad categories of privacy-preserving techniques including homomorphic encryption, secure multiparty computation, secure enclaves, and zero-knowledge proofs. Then we discuss some of the security considerations related to using these methods, potential use cases, and a conceptual system design for applying privacy-preserving methods in international safeguards.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2021

Cylinder Occupancy and Measurement Suite

This software automatically records data from the Unattended Cylinder Verification Station, determines the state of the instrument, captures images of uranium hexafluoride shipment cylinders, and determines their weight. The code has been developed primarily for the International Atomic Energy Agency, but this type of instrument could be of interest to any facility operator in the uranium supply chain that handles uranium hexafluoride shipment cylinders (e.g. the 30B and 48Y cylinder). Operators may be interested in having this instrument confirm shipper declared measurement values upon receipt of a cylinder. They may also use it to aid in process monitoring if the quantity of material in the cylinder changes due to a processing activity.

Stewart, Scott L↗
DOE OSTI2020

Considerations for using Privacy Preserving Machine Learning Techniques for Safeguards

In international nuclear safeguards, the International Atomic Energy Agency (IAEA) is tasked with inspecting and verifying nuclear facilities and their activities. Data analytics and machine learning to support inspections require large amounts of data that nuclear facility operators may consider proprietary or sensitive, so the IAEA may not have full access. Allowing computation over private data without compromising its security therefore has value for safeguards inspections and analysis. Privacy-preserving machine learning (PPML) consists of security-focused techniques that allow data analytics and machine learning algorithms to run on sensitive data without revealing it. This includes ideas like homomorphic encryption (HE), secure multiparty computation (SMPC), and secure enclaves. HE allows algorithms and mathematical operations to be conducted directly on the encrypted data instead of first decrypting it. With SMPC, multiple entities collaboratively compute over distributed data such that no party is able to directly view any others’ original data. Secure enclaves allow computation to take place in a separate and heavily blocked-off section of a CPU. Techniques like these allow for several potential use cases in which the security of data is essential. With SMPC, machine learning models can be trained over the input data from multiple entities, resulting in a model that all users can benefit from without leaking the input data from any particular entity. With SMPC or a zero-knowledge proof (ZKP), an algorithm returning some single answer or truth value can be run on someone else’s data without ever needing to see that data, potentially allowing for verification or proof of some underlying question. HE can allow for outsourcing computation on data to a hostile or untrusted environment. Although most of the research in this field resides within the health and financial domains, tools from PPML may have similar applications in nuclear safeguards. Allowing the IAEA to compute over proprietary information, such as process models and raw sensor data using PPML techniques, provides the baseline for running complex analytics without needing direct unencrypted access to the underlying data, maintaining its privacy. Important limitations to consider for these techniques include the efficiency and level of security required. The security of HE and SMPC come at the cost of speed—the significant amount of overhead means that algorithms implemented in these protocols and encryption schemes are slower than when run on plaintext. Additionally, several important parameters determine what techniques or protocols are used based on the security requirements. SMPC protocols may need to be selected for resistance against a party that attempts to deviate from the protocol to distort the result or gain access to additional information, and a protocol secure against these attacks may further increase the overhead of the algorithm.

97 MATHEMATICS AND COMPUTING↗