Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 1846969

Vulnerabilities in Artificial Intelligence and Machine Learning Applications and Data

Eggers, Shannon Leigh·Sample, Char
View original source ↗Read source document ↗Export metadata ↓

Abstract

Artificial intelligence (AI) applications driven by machine learning (ML) are transformational technologies within the international nuclear security regime. Advancements realized by AI—faster and improved data insights, more efficient and automated processes, reductions in human error—enable nuclear security applications such as behavior analysis for insider threat mitigation, source tracking of stolen nuclear material, and facial recognition software for physical protection. In addition to the advantages, however, there are also inherent vulnerabilities and threats associated with its use and risk mitigations must be built into any AI/ML-enabled systems. This work provides a background on AI and ML and different data types used in the field, including open-source intelligence information (OSINT) that is discoverable by AI tools and application data that are used by AI tools for decision-making and automation. Current and potential AI applications and vulnerabilities related to their use within the nuclear security regime are also discussed.

Explore related subjects

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE97 MATHEMATICS AND COMPUTING98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL PROTECTIONadversarial AIAI/MLartificial intelligencemachine learningnuclear security

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Eggers, Shannon Leigh, Sample, Char. 2020-12-01. Vulnerabilities in Artificial Intelligence and Machine Learning Applications and Data. https://doi.org/10.2172/1846969

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

Morgana Overview – NCERC Support for Dynamic Subcritical Experiments

The LANL Subcritical Experiments Program (SCE) recently executed the Morgana Subcritical Experiment at the NNSS. This was the first subcritical experiment executed by LANL for several years (since 2021). It was also notably the first that required SCE personnel to have FMH qualifications for a portion of the work conducted under nuclear criticality safety limits.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2026

AWSD Reactive Burn Model for the HMX‐Based High Explosive LX‐04

An Arrhenius–Wescott–Stewart–Davis (AWSD) reactive burn model is applied to describe shock initiation and detonation properties of the HMX-based high explosive LX-04. The parameters in the model are calibrated to data from multiple sources. The thermodynamic equations of state used in the model are calibrated to a combination of thermochemical calculations for HMX and LX-04 as well as experimentally-measured cylinder expansion results for LX-04. The kinetic parameters are calibrated to velocity data from gas gun experiments performed using EDC-32—a high explosive with the same chemical composition as LX-04 but different structural properties, and scaled rate stick data for PBX 9012. The AWSD model is shown to accurately describe the shock initiation and propagation of LX-04. Very good agreement is observed between the available experimental data and the AWSD model output. The presented results constitute an accurate LX-04 reactive burn model for use in engineering-scale models and simulations.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2026

Surface and Buried Thermal, and RGB Unexploded Ordnance Data Collection

This document provides a description of a data collection campaign of unexploded ordnance (UXOI) set. The dataset captures a controlled UAV imaging campaign designed to support detection of UXO across varied environmental conditions. Data were collected during three campaigns in Norris and Northeast Knoxville, Tennessee, using RGB, and thermal sensors mounted on Parrot UKR. In total, the dataset contains 9925 images, 26 full-motion video, and approximately 81.99 GB of data, collected across late spring/summer conditions, every hour during sunlight, and multiple surface contexts, including tall grass, short grass, gravel, as well as buried in sand, and other gravel mixtures. The collection was designed to capture thermal and visual variability relevant to UXO detection in agricultural land, bare earth, and subsurface. Review of the imagery showed that ordnance was most detectable during periods of changing solar input, especially approximately 10-60 minutes after sunrise, approximately 20-60 minutes after sunset, and 2-3 min after cloud cover interrupted prolonged solar heating. These conditions increased thermal contrast because many ordnance items retained or released heat differently than the surrounding vegetation and ground surface. This dataset provides a useful resource for developing and evaluating airborne UXO detection methods under realistic field conditions. All ordnance used in the study was inert, and thermal behavior may differ from that of live ordnance. In addition, variation in ordnance type, composition, and placement introduced differences in thermal response that should be considered when interpreting results.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗