Search NASA⌕ Search

SEARCH · Search NASA

Results for “adversarial robustness”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Improving multiwell petrophysical interpretation from well logs via machine learning and statistical models

Well-log interpretation estimates in situ rock properties along well trajectory, such as porosity, water saturation, and permeability, to support reserve-volume estimation, production forecasts, and decision making in reservoir development. However, due to measurement errors, variability of well logs caused by multiple measurement vendors, different borehole tools, and nonuniform drilling/borehole conditions, estimations of rock properties with original well logs without proper preprocessing may not be accurate, especially in the context of multiwell estimation. Well-log normalization techniques such as two-point scaling and mean-variance normalization are commonly used to improve the robustness of multiwell rock-property estimation. However, these techniques do not consider the correlation between well logs and require subjective knowledge for their effective implementation. To reduce uncertainties and processing time associated with multiwell rock-property estimation from well logs, we develop discriminative adversarial (DA) and linear constraint models for well-log normalization and rock-property estimation. The DA neural network model developed for well-log normalization and interpretation can perform linear and nonlinear well-log normalization while considering the joint distribution of each well log and rock properties. However, the linear constraint model uses an ensemble of predictions from linear models to constrain well-log normalization and rock-property estimation. We also develop a divergence-based type well identification method to select type (training) wells for a test well based on the statistical similarity of associated well-log distributions instead of the interwell distance. We apply the DA model to perform well-log normalization and prediction of permeability for the Seminole San Andres Unit carbonate reservoir. Compared with the permeability predicted with the classical machine learning model without well-log normalization and models with two-point scaling normalization, the DA model yields the most accurate permeability prediction by decreasing the mean-squared error of permeability prediction by 20%–50%.

Geochemistry & Geophysics↗
DOE OSTI2025

Persistent Classification: Understanding Adversarial Attacks by Studying Decision Boundary Dynamics

ABSTRACT There are a number of hypotheses underlying the existence of adversarial examples for classification problems. These include the high‐dimensionality of the data, the high codimension in the ambient space of the data manifolds of interest, and that the structure of machine learning models may encourage classifiers to develop decision boundaries close to data points. This article proposes a new framework for studying adversarial examples that does not depend directly on the distance to the decision boundary. Similarly to the smoothed classifier literature, we define a (natural or adversarial) data point to be ( γ , σ)‐stable if the probability of the same classification is at least for points sampled in a Gaussian neighborhood of the point with a given standard deviation . We focus on studying the differences between persistence metrics along interpolants of natural and adversarial points. We show that adversarial examples have significantly lower persistence than natural examples for large neural networks in the context of the MNIST and ImageNet datasets. We connect this lack of persistence with decision boundary geometry by measuring angles of interpolants with respect to decision boundaries. Finally, we connect this approach with robustness by developing a manifold alignment gradient metric and demonstrating the increase in robustness that can be achieved when training with the addition of this metric.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Emerging Threats in Transportation Security Related to Intelligent Transportation Systems (ITS)

Transport of high-consequence shipments requires a resilient and robust systems of systems to guarantee cargo arrival. Furthermore, rising adoption of technologies such as connected and automated vehicles (CAVs), intelligent infrastructure, and vehicle-to-everything (V2X) communication presents unique challenges for securing transportation systems. Within these Intelligent Transportation Systems (ITS), several additional vulnerabilities exist that create pathways for adversarial attacks and cargo interception. For example, connectivity provides cyber pathways directly into vehicle systems and infrastructure for malicious actors. Furthermore, advanced vehicle automation exposes additional vehicle control necessary for shipment interception otherwise unavailable to adversaries. Within this paper, we will discuss the specific threats introduced by ITS-enabled technologies currently deployed and in development. These include those mentioned related to connectivity and automation, but will be expanded into grid, infrastructure, and vehicle specific threats. In addition, we will discuss how to potentially mitigate these emerging challenges as well as how to safeguard transportation systems from next generation attacks.

Cook, Adian [ORNL] (ORCID:0000000160825395)↗
DOE OSTI2024

Deep-learning based artificial intelligence tool for melt pools and defect segmentation

Accelerating fabrication of additively manufactured components with precise microstructures is important for quality and qualification of built parts, as well as for a fundamental understanding of process improvement. Accomplishing this requires fast and robust characterization of melt pool geometries and structural defects in images. This paper proposes a pragmatic approach based on implementation of deep learning models and self-consistent workflow that enable systematic segmentation of defects and melt pools in optical images. Deep learning is based on an image-to-image translation–conditional generative adversarial neural network architecture. An artificial intelligence (AI) tool based on this deep learning model enables fast and incrementally more accurate predictions of the prevalent geometric features, including melt pool boundaries and printing-induced structural defects. We present statistical analysis of geometric features that is enabled by the AI tool, showing strong spatial correlation of defects and the melt pool boundaries. The correlations of widths and heights of melt pools with dataset processing parameters show the highest sensitivity to thermal influences resulting from laser passes in adjacent and subsequent layer passes. The presented models and tools are demonstrated on the aluminum alloy and datasets produced with different sets of processing parameters. However, they have universal quality and could easily be adapted to different material compositions. The method can be easily generalized to microstructural characterizations other than optical microscopy.

additive manufacturing↗
DOE OSTI2025

SURVEILLANCE DETECTION FOR TRANSPORTATION OPERATIONS PERSONNEL TO PREVENT HIJACKING, THEFT, SABOTAGE, AND MALICIOUS SECURITY EVENTS DURING TRANSPORTING NUCLEAR MATERIAL

The secure transportation of high-consequence materials, including nuclear and radiological assets, is a critical global priority in the face of escalating terrorism, security threats, and violent protests targeting these operations. Effective surveillance detection—the ability to identify, assess, and respond to potential threats across a continuum of scenarios—is paramount in addressing these challenges. This paper outlines a phased, multi-tiered training program designed to strengthen the surveillance detection capabilities of organizations responsible for nuclear material transport. The proposed training program adopts a progressive approach, gradually increasing in technical complexity to provide participants with comprehensive knowledge and tools for implementing robust security strategies. It targets a wide spectrum of stakeholders, including competent authorities, regulators, inspectors, shippers, carriers, law enforcement, and emergency response personnel, equipping them to plan, evaluate, and safeguard nuclear material transportation effectively. Each phase of the program emphasizes distinct elements of the surveillance detection continuum and transport security, focusing on critical topics such as threat identification, adversary task timelines, protective methodologies, and attack mitigation strategies. The training framework is anchored in technical exchanges and scenario-driven courses that reflect real-world complexities and challenges. By addressing the surveillance detection continuum comprehensively—from early threat assessment to active countermeasures—the program reinforces global efforts to secure nuclear assets. It aligns with international security objectives and fosters a strong security culture within participating organizations, ensuring personnel are prepared to counter potential threats and maintain the safe, secure movement of these materials. Ultimately, this initiative aims to enhance preparedness, security, and response capabilities, supporting the global mission to safeguard high-consequence materials against evolving threats.

Zineddin, Dr. Z. [ORNL] (ORCID:0009000848740725)↗
NASA NTRSDate not supplied

NEUROSPF: A Tool For the Symbolic Analysis of Neural Networks

This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representation that is amenable for analysis using the Symbolic PathFinder symbolic execution tool. Notably, NEUROSPF encodes specialized peer classes for parsing the model’s parameters, thereby enabling efficient analysis. With NEUROSPF the user has the flexibility to specify either the inputs or the network internal parameters as symbolic, promoting the application of program analysis and testing approaches from software engineering to the field of machine learning. For instance, NEUROSPF can be used for coverage-based testing and test generation, finding adversarial examples and also constraint-based repair of neural networks, thus improving the reliability of neural networks and of the applications that use them.

neural networks↗
DOE OSTI2021

PhaseGAN: a deep-learning phase-retrieval approach for unpaired datasets

Phase retrieval approaches based on deep learning (DL) provide a framework to obtain phase information from an intensity hologram or diffraction pattern in a robust manner and in real-time. However, current DL architectures applied to the phase problem rely on i) paired datasets, i. e., they arc only applicable when a satisfactory solution of the phase problem has been found, and ii) the fact that most of them ignore the physics of the imaging process. Here, we present PhaseGAN, a new DL approach based on Generative Adversarial Networks, which allows the use of unpaired datasets and includes the physics of image formation. The performance of our approach is enhanced by including the image formation physics and a novel Fourier loss function, providing phase reconstructions when conventional phase retrieval algorithms fail, such as ultra-fast experiments. Thus, PhaseGAN offers the opportunity to address the phase problem in real-time when no phase reconstructions but good simulations or data from other experiments are available.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Data efficiency assessment of generative adversarial networks in energy applications

This study investigates the data requirements of generative artificial intelligence (AI), particularly generative adversarial networks (GANs), for reliable data augmentation in energy applications. Generative AI, though seen as a solution to data limitations, requires substantial data to learn meaningful distributions—a challenge often overlooked. This study addresses the challenge through synthetic data generation for critical heat flux (CHF) and power grid demand, focusing on renewable and nuclear energy. Two variants of GAN employed are conditional GAN (cGAN) and Wasserstein GAN (wGAN). Our findings include the strong dependency of GAN on data size, with performance declining on smaller datasets and varying performance when generalizing to unseen experiments. Mass flux and heated length significantly influence CHF predictions. wGAN is more robust to feature exclusion, making it suitable for constrained synthetic data generation. In energy demand forecasting, wGAN performed well for solar, wind, and load predictions. Longer lookback hours and larger datasets improved predictions, especially for load power. Seasonal variations posed challenges, with wGAN achieving a relatively high error of Root Mean Squared Error (RMSE) of 0.32 for load power prediction, compared to RMSE of 0.07 under same-season conditions. Feature exclusions impacted cGAN the most, while wGAN showed greater robustness. This study concludes that, while generative AI is effective for data augmentation, it requires substantial data and careful training to generate realistic synthetic data and generalize to new experiments in engineering applications.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

DEReliction: A Cybersecurity Vulnerability Assessment Methodology for Distributed Energy Resources

With the increasing integration of Distributed Energy Resources (DER) into the electric grid, maintaining grid reliability and resilience requires that these devices remain secure. This paper discusses a cybersecurity vulnerability assessment methodology that incorporates best practices from Sandia National Laboratories, SANS Institute, OWASP Foundation, and other web and Internet of Things (IoT) penetration testing (“pen testing”) programs, courses, and frameworks for assessing the security posture of devices. The methodology involves five sequential steps: (1) Collect Public Information, (2) Extract Hardware Details, (3) Inventory Software Components, (4) Identify Vulnerabilities, and (5) Test Vulnerabilities. Each step uncovers potential weaknesses in both hardware and software components of DER devices, considering adversary tactics, techniques, and procedures (TTPs), and potential attack vectors along the way. The results from the execution of this method on multiple residential- and small commercial-scale photovoltaic (PV) inverters reveled hardware and software vulnerabilities, which highlight the benefit of taking a methodical approach to discover vulnerabilities. While the specific vulnerability details are not shared here, a generalized overview of findings underscore the importance of robust security assessments for DER devices. Adoption of an assessment framework of this kind will identify and mitigate cybersecurity threats and bolster the resilience of DER-integrated electric grids.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques— Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)— and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ~20%. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

galaxies: interactions↗
DOE OSTI2021

BioSecure Digital Twin: Manufacturing Innovation and Cybersecurity Resilience

U.S. national security, prosperity, economy, and well-being require secure, flexible, and resilient Biopharmaceutical Manufacturing. The COVID-19 pandemic reaffirmed that the biomedical production value-chain is vulnerable to disruption and has been under attack from sophisticated nation-state adversaries. Current cyber defenses are inadequate, and the integrity of critical production systems and processes are inherently vulnerable to cyber-attacks, human error, and supply chain disruptions. The following chapter explores how a BioSecure Digital Twin will improve U.S. manufacturing resilience and preparedness to respond to these hazards by significantly improving monitoring, integrity, security, and agility of our manufacturing infrastructure and systems. The BioSecure Digital Twin combines a scalable manufacturing framework with a robust platform for monitoring and control to increase U.S. biopharma manufacturing resilience. Then, the chapter discusses some of the inherent vulnerabilities and challenges at the nexus of health and advanced manufacturing. Next, the chapter highlights that as the Pandemic evolves, we need agility and resilience to overcome significant obstacles. This section highlights an innovative application of Cyber Informed Engineering to developing and deploying a BioSecure Digital Twin to improve the resilience and security of the biopharma industrial supply chain and production processes. Finally, the chapter concludes with a process framework to complement the Digital Twin platform, called the Biopharma (Observe, Orient, Decide, Act) OODA Loop Framework (BOLF), a four-step approach to decision-making outputs from the Digital Twin. The BOLF will help end users leverage twin technology by distilling the available information, focusing the data on context, and rapidly making the best decision while remaining cognizant of changes that can be made as more data becomes available.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram

X-ray phase contrast imaging significantly improves the visualization of structures with weak or uniform absorption, broadening its applications across a wide range of scientific disciplines. Propagation-based phase contrast is particularly suitable for time- or dose-critical in vivo/in situ/operando (tomography) experiments because it requires only a single intensity measurement. However, the phase information of the wave field is lost during the measurement and must be recovered. Conventional algebraic and iterative methods often rely on specific approximations or boundary conditions that may not be met by many samples or experimental setups. In addition, they require manual tuning of reconstruction parameters by experts, making them less adaptable for complex or variable conditions. Here we present a self-learning approach for solving the inverse problem of phase retrieval in the near-field regime of Fresnel theory using a single intensity measurement (hologram). A physics-informed generative adversarial network is employed to reconstruct both the phase and absorbance of the unpropagated wave field in the sample plane from a single hologram. Unlike most state-of-the-art deep learning approaches for phase retrieval, our approach does not require paired, unpaired, or simulated training data. This significantly broadens the applicability of our approach, as acquiring or generating suitable training data remains a major challenge due to the wide variability in sample types and experimental configurations. The algorithm demonstrates robust and consistent performance across diverse imaging conditions and sample types, delivering quantitative, high-quality reconstructions for both simulated data and experimental datasets acquired at beamline P05 at PETRA III (DESY, Hamburg), operated by Helmholtz-Zentrum Hereon. Furthermore, it enables the simultaneous retrieval of both phase and absorption information.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Safe and Robust Binary Classification and Fault Detection Using Reinforcement Learning

In this paper, we propose a learning-based method utilizing the Soft Actor-Critic (SAC) algorithm to train a binary Support Vector Machine (SVM) classifier. This classifier is designed to identify valid input spaces in high-dimensional, highly constrained systems while minimizing the total runtime of offline simulations. The simulations adapt their runtime based on the likelihood that a given training input will be informative to the classifier. Furthermore, we introduce a method for using the trained SAC model to predict whether a desired system input is likely to violate constraints, along with a technique to adjust the input as necessary. Additionally, we explore the potential of this model to detect faults or adversarial attacks within the system. The effectiveness of our approach is demonstrated through various simulations of challenging classification problems and a constrained quadrotor model.

Netter, Josh [Georgia Institute of Technology, Atl↗
DOE OSTI2024

Retrieval Augmented Generation for Robust Cyber Defense

In cybersecurity, the ability to efficiently analyze and respond to vulnerabilities, weaknesses, attack patterns, and threat tactics is critical for effective defense strategies. With the increasing complexity and volume of cybersecurity data, traditional methods of querying and retrieving information are often inadequate. To address this challenge, we implemented Retrieval-Augmented Generation (RAG) systems—CyRAG and GraphCyRAG—that integrate large language models (LLMs) with both structured data from relational databases and knowledge graphs such as Neo4j. CyRAG is designed to handle structured data, focusing on CVE (Common Vulnerabilities and Exposures) and CWE (Common Weakness Enumeration) entities to generate accurate and context-rich responses. In contrast, GraphCyRAG leverages Neo4j knowledge graphs to retrieve interconnected information from CVE, CWE, CAPEC (Common Attack Pattern Enumeration and Classification), and ATT&CK (Adversarial Tactics, Techniques, and Common Knowledge) datasets. By utilizing Neo4j’s graph-based framework, GraphCyRAG enables deeper traversal of relationships between vulnerabilities and attack patterns, providing cybersecurity analysts with more comprehensive insights into potential attack vectors and mitigation strategies. Our preliminary results demonstrate that integrating knowledge graphs with RAG significantly enhances both the accuracy and depth of threat analysis, allowing for the retrieval of dynamic, real-time data and the generation of contextually aware responses. This approach helps analysts uncover hidden relationships between cyber entities, predict exploit paths, and prioritize mitigation efforts effectively. The integration of RAG with cybersecurity knowledge graphs represents a significant advancement in cybersecurity threat intelligence, enabling more informed decision-making and stronger defense strategies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Decentralised Reinforcement Learning for Dynamic Cyberattack Response in Microgrid Networks

Microgrids rely on communication networks for reliable operation, which makes them inherently vulnerable to cyberattacks. Such attacks can destabilise system dynamics and drive states away from their nominal operating trajectories. Although several physics-informed and machine learning-based strategies have been developed to counter these threats, the rapidly evolving cyber landscape enables adversaries to bypass static defences or rules-based mitigation approaches. This paper proposes a dynamic, online-trained and fully decentralised reinforcement learning (RL)-based cyberattack response framework to protect microgrids from evolving cyberattacks. The proposed framework deploys multiple deep Q-networks (DQNs), each associated with a distributed energy resource (DER), to enable localised and adaptive attack mitigation. In this framework, each DQN processes local voltage and frequency measurements—combined with intrusion detection system (IDS) alerts—as observations and rewards to guide decision-making. Extensive simulation studies demonstrate the robustness of the proposed framework under diverse attack scenarios and varying IDS-induced detection delays. Comparative analysis highlights its superiority over existing static or preexisting rules-based mitigation approaches. Finally, we present an analysis that shows the framework's scalability to real-life microgrids with more interacting agents.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Edge ML for CAN bus intrusion detection in AVs

Autonomous Vehicles (AVs) are revolutionizing transportation, but their reliance on interconnected cyber-physical systems exposes them to unprecedented cybersecurity risks. This study addresses the critical challenge of detecting real-time cyber intrusions in self-driving vehicles by leveraging a dataset from the Udacity self-driving car project. We simulate four high-impact attack vectors, Denial of Service (DoS), spoofing, replay, and fuzzy attacks, by injecting noise into spatial features (e.g., bounding box coordinates) to replicate adversarial scenarios. We develop and evaluate two lightweight neural network architectures (NN-1 and NN-2) alongside a logistic regression baseline (LG-1) for intrusion detection. The models achieve exceptional performance, with NN-2 attaining an AUC score of 93.15% and 93.15% accuracy, demonstrating their suitability for edge deployment in AV environments. Through explainable AI techniques, we uncover unique forensic fingerprints of each attack type, such as spatial corruption in fuzzy attacks and temporal anomalies in replay attacks, offering actionable insights for feature engineering and proactive defense. Visual analytics, including confusion matrices, ROC curves, and feature importance plots, validate the models' robustness and interpretability. This research sets a new benchmark for AV cybersecurity, delivering a scalable, field-ready toolkit for Original Equipment Manufacturers (OEMs) and policymakers. By aligning intrusion fingerprints with SAE J3061 automotive security standards, we provide a pathway for integrating machine learning into safety-critical AV systems. Our findings underscore the urgent need for security-by-design AI, ensuring that AVs not only drive autonomously but also defend autonomously. This work bridges the gap between theoretical cybersecurity and life-preserving engineering, offering a leap toward safer, more secure autonomous transportation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

MetaHeart: Metasurface enabled biometrics camouflage

Privacy-invading biometrics monitoring is becoming a prominent security threat as modern sensing systems move to higher operating frequencies (mmWave, sub-THz), increasing sensing resolution and accuracy. As such, developing systems that can protect or obfuscate biometrics from adversarial intrusion becomes pivotal to preserving user privacy. In this work, we develop and implement MetaHeart, a real-time biometrics misinformation system based on reflective, programmable metasurfaces and dynamic phase-front manipulation of radar inferences. MetaHeart’s key goal is to prevent the leakage of a legitimate user’s heartbeat biometrics by spoofing fake heartbeat signals at a malicious, radar-equipped, heart rate sensing intruder. Furthermore, we experimentally demonstrate MetaHeart’s ability to fake Alice’s presence when she is not there and to fool Trudy’s inferences even when Alice is present, achieving an overall accuracy above 98%. Finally, we conduct a robustness analysis to determine MetaHeart’s required spatial placement within the intruder’s monitoring area that would allow for effective spoofing.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2025

TRIM: AI Guided Random Number Generation for Resource-Constrained IoT Systems

Random numbers often serve as the backbone for many security solutions in diverse domains such as cryptography, side channel leakage prevention, and moving target defense. However, generating true random numbers requires a physical source of entropy (e.g. hardware, quantum, environmental phenomenon) making it difficult to realize at a large scale and at a low cost. On the flip side, pseudorandom number generators (easy to implement) following a specific distribution (e.g. Gaussian) can be easily compromised given a sufficient amount of traces. In this work, we have developed a machine learning-guided generative approach that can be used to create portable, resource-efficient, and cost-effective random number generators with high throughput and true randomness characteristics. We implement the proposed approach as a highly parameterized framework and perform extensive evaluation for different settings. The framework was able to learn from true random sources such as irrational numbers and environmental audio noise and imitate those sources towards generating new good quality random numbers on demand. We have generated more than 1 billion bits and observed robust performance in terms of true randomness metrics obtained from NIST SP 800-22 and FIPS 140-1 randomness test suites achieving a throughput of up to 142.85 Mbps. Compared to the state-of-the-art (SOTA) technique, the iso-cost setup of our framework can achieve more than 500 Mbps in a distributed setting. We have evaluated the efficacy of running the true randomness imitation AI models on target edge devices such as Raspberry Pi 4 (Model B), Nvidia Jetson Nano, Nvidia Jetson Orin Nano and Nvidia Jetson Xavier. We have also looked at the security of the TRIM framework itself against different adversarial threat models.

Cybersecurity↗