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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Tamper-Indicating Enclosures with Visually Obvious Tamper Response

Sandia National Laboratories is developing a way to visualize molecular changes that indicate penetration of a tamper-indicating enclosure (TIE). Such "bleeding" materials (analogous to visually obvious, colorful bruised skin that doesn't heal) allows inspectors to use simple visual observation to readily recognize that penetration into a material used as a TIE has been attempted, without providing adversaries the ability to repair damage. Such a material can significantly enhance the current capability for TIEs, used to support treaty verification regimes. Current approaches rely on time-consuming and subjective visual assessment by an inspector, external equipment, such as eddy current or camera devices, or active approaches that may be limited due to application environment. The complexity of securing whole volumes includes: (1) enclosures that are non-standard in size/shape; (2) enclosures that may be inspectorate- or facility-owned; (3) tamper attempts that are detectable but difficult or timely for an inspector to locate; (4) the requirement for solutions that are robust regarding reliability and environment (including facility handling); and (5) the need for solutions that prevent adversaries from repairing penetrations. The approach is based on a transition metal ion solution within a microsphere changing color irreversibly when the microsphere is ruptured. Investigators examine 3D printing of the microspheres as well as the spray coating formulation. The anticipated benefits of this work are passive, flexible, scalable, cost-effective TIEs with obvious and robust responses to tamper attempts. This results in more efficient and effective monitoring, as inspectors will require little or no additional equipment and will be able to detect tamper without extensive time-consuming visual examination. Applications can include custom TIEs (cabinets or equipment enclosures), spray-coating onto facility-owned items, spray-coating of walls or structures, spray-coatings of circuit boards, and 3D-printed seal bodies. The paper describes research to-date on the sensor compounds and microspheres.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2026

CTGAN-TVAE

SAND2026-18914O CTGAN-TVAE (Conditional Tabular Generative Adversarial Networks-Tabular Variational Autoencoders) generates extensive sets of variable generation data through a hybrid framework. It enhances latent space representation by combining TVAE's robust feature-embedding with CTGAN's ability to condition categorical variables such as time. CTGAN-TVAE employs a fully connected neural network within a conditional generative adversarial network framework to manage continuous and categorical data effectively, capturing complex feature interactions without needing sequential modeling. This was developed as part of NNSA-MSIPP: Minority Serving Institution Partnership Program, Grant Number DE-NA0004016. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA0003525.

Newlun, Cody [Sandia National Lab. (SNL-CA), Liver↗
DOE OSTI2026

3D reconstruction and neural rendering for adversarial machine learning

While evasion attacks on computer vision systems have been widely studied, creating attacks that remain effective under significant changes in viewpoint continues to be challenging. Traditional approaches often rely on affine transformations of images, but these approaches degrade at larger perspective shifts and often produce unrealistic or ineffective perturbations. Recent methods use differentiable renderers to improve viewpoint robustness, but they typically depend on manually constructed 3D models. We introduce a semi-automated pipeline that generates physically printable and perspective-invariant adversarial patches using only a small set of 2D images. Our method integrates 3D reconstruction, neural rendering, adversarial patch optimization, and an object detection victim model into a unified workflow. We use 2D Gaussian Splatting for high fidelity mesh reconstruction and FlexPara for surface parameterization that produces texture maps suitable for patch editing. Together, these components form a fully differentiable pipeline in PyTorch3D that links texture modification to model outputs, enabling efficient optimization of patches that remain effective across many viewpoints. The complete process, from image capture to patch printing and physical evaluation, can be completed within a few hours. We demonstrate the effectiveness of the resulting patches through attacks on the YOLOv8 object detection model and discuss remaining challenges and opportunities for improving robustness and scalability.

Singhvi, Vivaan [ORNL] (ORCID:0009000586288221)↗
DOE OSTI2024

Finding MIDDLE Ground: Scalable and Secure Distributed Learning

Edge computing methods allow devices to efficiently train a high-performing, robust, and personalized model for predictive tasks. However, these methods succumb to privacy and scalability concerns such as adversarial data recovery and expensive model communication. Furthermore, edge computing methods unrealistically assume that all devices train an identical model. In practice, edge devices have varying computational and memory constraints which may not allow certain devices to have the space or speed to train a specific model. To overcome these issues, we propose MIDDLE: a model independent distributed learning algorithm which allows heterogeneous edge devices to assist each other’s training while communicating only non-sensitive information. MIDDLE unlocks the ability for edge devices, regardless of computational or memory constraints, to assist each other even with completely different model architectures. Furthermore, MIDDLE does not require model or gradient communication which greatly reduces communication size and time. We prove that MIDDLE attains the optimal convergence rate O(1/sqrt(TM)) of stochastic gradient descent for convex and non-convex smooth optimization (for total iterations T and batch size M). Finally, our experimental results demonstrate that MIDDLE (even in non-IID data settings) attains robust and high-performing models without model or gradient communication.

Bornstein, Marc I.↗
DOE OSTI2022

High-precision inversion of dynamic radiography using hydrodynamic features

While radiography is routinely used to probe complex, evolving density fields in research areas ranging from materials science to shock physics to inertial confinement fusion and other national security applications, complications resulting from noise, scatter, complex beam dynamics, etc. prevent current methods of reconstructing density from being accurate enough to identify the underlying physics with sufficient confidence. In this work, we show that using only features that are robustly identifiable in radiographs and combining them with the underlying hydrodynamic equations of motion using a machine learning approach of a conditional generative adversarial network (cGAN) provides a new and effective approach to determine density fields from a dynamic sequence of radiographs. In particular, we demonstrate the ability of this method to outperform a traditional, direct radiograph to density reconstruction in the presence of scatter, even when relatively small amounts of scatter are present. Our experiments on synthetic data show that the approach can produce high quality, robust reconstructions. We also show that the distance (in feature space) between a testing radiograph and the training set can serve as a diagnostic of the accuracy of the reconstruction.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS2020

CyberGAN: Generating High-fidelity Cybersecurity Data With Generative Adversarial Networks

Machine learning for cyber defense offers the promise of detecting adversarial activity against the ground data systems managing critical space assets. A fundamental challenge facing machine learning research in cybersecurity is the lack of high-fidelity, shareable datasets for robust evaluation and testing of machine learning-based solutions. High-fidelity, real-world datasets are necessary for reliable benchmarking of nominal system behavior and malicious activity. Unfortunately, such realistic datasets of both nominal and adversarial activity are rarely shared publicly by data owners due to security and privacy concerns. Besides, the available adversarial data is sparse, which makes training models on malicious activity much harder. This situation has impeded and continues to impede the research and successful adoption of machine learning methods for cyber defense. Researchers have dealt with this problem by generating data within a low-fidelity lab environment, using classified and thus unshareable datasets, or downloading low-fidelity public datasets made available by others. We propose an innovative solution to the problem by employing machine learning methods to generate high-fidelity data. Specifically, we propose the use of Generative Adversarial Networks (GANs) to generate high-fidelity data for cybersecurity purposes. GANs have found successful image processing and natural language applications, but have not yet been investigated for cyber data generation. Our proposed approach first involves training the `discriminator' network of the GAN with a sample of real-world data consisting of malicious and nominal samples. We then use the `generator' network to generate new high-fidelity data samples consisting of an appropriate mix of malicious and nominal activity. We demonstrate applications of our architecture by generating high-fidelity cybersecurity data containing both malicious and nominal samples. We thoroughly evaluate the fidelity of our generated data using heuristics and evaluate its usefulness for machine learning applications using three different datasets. Overall, our approach results in high-fidelity, shareable datasets.

Zhang, Yuening↗
DOE OSTI2020

Reliable machine prognostic health management in the presence of missing data

Prognostics and health management enables the prediction of future degradation and remaining useful life (RUL) for in-service systems based on historical and contemporary data, showing promise for many practical applications. One major challenge for prognostics is the common occurrence of missing values in time-series data, often caused by disruptions in sensor communication or hardware/software failures. Another major concern is that the sufficient prior knowledge of critical component degradation with a clear failure threshold is often not readily available in practice. These issues can significantly hinder the application of advanced signal and data analysis methods and consequently degrade the health management performance. In this article, we propose a novel data-driven framework that is capable of providing accurate and reliable predictions of degradation and RUL. In this approach, one-hot health state indicators are appended to the historical time series so that the model learns end-of-life automatically. A modified gate recurrent unit based variational autoencoder is employed in generative adversarial networks to model the temporal irregularity of the incomplete time series. Furthermore, experiments on multivariate time-series datasets collected from real-world aeroengines verify that significant performance improvement can be achieved using the proposed model for robust long-term prognostics.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
NASA NTRSDate not supplied

An Inverse Chance-constrained Approach to the Calibration of Robust Models

This paper proposes a strategy to calibrate computational models according to uncertain input-output data. To this end, uncertainty in the data is first quantified by creating adversarial data sets. Samples drawn from such sets are then mapped from the input-output space to the parameter space using an inverse mapping. This mapping minimizes the collective output spread of an ensemble of point predictions while satisfying a set of individual data-matching requirements. The distribution of the resulting parameter points, which often exhibits strong parameter dependencies, is then modeled using sliced-normals. The chance-constrained formulation used to learn this distribution enables the analyst to trade-off a greater likelihood for most of the data against a lower likelihood for some of the data thereby relaxing the conservatism of the calibrated model. This formulation not only neglects the worst-performing quantiles of each adversarial distribution but also eliminates the potentially serious effects that outliers might have on the resulting model. This calibration approach not only has a considerably lower computational cost than the standard forward approach but it also allows for the identification of suitable distribution classes, which in turn yield better calibrated models.

Calibration↗
DOE OSTI2022

DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification

With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of ${\approx}2.3$ the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks

The evaluation of constitutive models, especially for high-risk and high-regret engineering applications, requires efficient and rigorous third-party calibration, validation and falsification. While there are numerous efforts to develop paradigms and standard procedures to validate models, difficulties may arise due to the sequential, manual, and often biased nature of the commonly adopted calibration and validation processes, thus slowing down data collections, hampering the progress towards discovering new physics, increasing expenses and possibly leading to misinterpretations of the credibility and application ranges of proposed models. This work attempts to introduce concepts from game theory and machine learning techniques to overcome many of these existing difficulties. Here, we introduce an automated meta-modeling game where two competing AI agents systematically generate experimental data to calibrate a given constitutive model and to explore its weakness such that the experiment design and model robustness can be improved through competitions. The two agents automatically search for the Nash equilibrium of the meta-modeling game in an adversarial reinforcement learning framework without human intervention. In particular, a protagonist agent seeks to find the more effective ways to generate data for model calibrations, while an adversary agent tries to find the most devastating test scenarios that expose the weaknesses of the constitutive model calibrated by the protagonist. By capturing all possible design options of the laboratory experiments into a single decision tree, we recast the design of experiments as a game of combinatorial moves that can be resolved through deep reinforcement learning by the two competing players. Our adversarial framework emulates idealized scientific collaborations and competitions among researchers to achieve a better understanding of the application range of the learned material laws and prevent misinterpretations caused by conventional AI-based third-party validation. Numerical examples are given to demonstrate the wide applicability of the proposed meta-modeling game with adversarial attacks on both human-crafted constitutive models and machine learning models.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

SafeDNN: Understanding and Verifying Neural Networks

The SafeDNN project at NASA Ames explores analysis techniques and tools to ensure that systems that use Deep Neural Networks (DNN) are safe, robust and interpretable. Research directions we are pursuing include: symbolic execution for DNN analysis, label-guided clustering to automatically identify input regions that are robust, parallel and compositional approaches to improve formal SMT-based verification, property inference and automated program repair for DNNs, adversarial training and detection, probabilistic reasoning for DNNs. In this talk I will highlight some of the research advances from SafeDNN, that were already published.

Corina Pasareanu↗
DOE OSTI2026

Cyote-attack Chain Estimator

Attack Chain Estimator (ACE) Application Overview The Attack Chain Estimator (ACE) Application is a sophisticated tool designed for the ingestion, classification, sequencing, and enrichment of cybersecurity threat reports. This application leverages advanced machine learning models and extensive historical data to provide comprehensive insights into cyber threats, specifically targeting Industrial Control Systems (ICS). Purpose The primary functions of the ACE Application include: Ingestion of Cybersecurity Threat Reporting: Capable of ingesting text-based threat reports in markdown or text file format. Supports ingestion of structured data from other sources in STIX/JSON format. Classification of Report’s Text-Based Events: Utilizes a DeBERTa classifier, specifically trained on cybersecurity data, to map the events to MITRE ATT&CK for ICS Tactics and Techniques. Classification is performed using multiple Jupyter notebooks and machine learning workflows hosted as FastAPI microservices: regex_data deberta_base_35_train_hft_classifier_mlflow.ipynb hft_regex_classifier_mlflow.ipynb param_train_hft_classifier_mlflow.ipynb regex_tactic_tech.ipynb Ordering of Tactics, Techniques, and Observable Events: Sequences the identified tactics, techniques, and events to form a coherent attack chain. Enrichment with Historical Attack Chain Details: Enhances the attack chain with details from historical attacks using a Markov model developed from CyOTE Precursor Analysis Report data. The Markov model is available as a FastAPI endpoint for seamless integration. Enrichment with Adversary Emulation Capabilities Data: Integrates adversary emulation capabilities data using MITRE Caldera for OT adversary abilities UUIDs. Export of Output Files: Provides options to export the enriched attack chain in JSON or CSV formats. Routing of Output to Other Applications: Facilitates routing of output to various platforms and applications, including: Threat Intelligence Platforms COREII Scout for Threat Intelligence Analysis COREII Modeling and Simulation for Adversary Emulation Technical Description The ACE Application is an advanced cybersecurity tool designed to provide detailed threat analysis and sequence generation. It is built on a robust architecture that integrates natural language processing, machine learning, and historical data modeling. Key Components: Data Ingestion Module: Handles the input of threat reports and data from various formats, ensuring flexibility in data sources. Classification Engine: Employs DeBERTa-based classifiers hosted as FastAPI microservices to analyze and classify threat report events in accordance with the MITRE ATT&CK framework for ICS. Sequence Generator: Orders the classified events into a logical attack chain, providing clear insight into the sequence of tactics and techniques used in the threat. Enrichment Engine: Integrates historical data and adversary emulation capabilities to enhance the attack chain with valuable context and additional details. The historical data enrichment is powered by a Markov model, which is available as a FastAPI endpoint. Export and Routing Module: Facilitates the export of the enriched attack chain in multiple formats and routes the output to designated applications for further analysis or emulation.

Paul, Tony [Idaho National Laboratory (INL), Idaho↗
DOE OSTI2025

Security Assessment of an LBP16-Protocol-Based Computer Numerical Control Machine

Subtractive manufacturing systems, specifically, computer numerical control machines, have revolutionized the manufacturing industry. Computer numerical control machining is the preferred method for producing finished parts due to its efficiency, speed and suitability for high-volume production. Securing computer numerical control machines is a priority. Compromises or disruptions of these machines can result in significant downtime, loss of productivity and financial loss. This study examines the vulnerabilities and risks associated with computer numerical control machines, in particular, systems utilizing the LBP16 protocol for controller-machine communications. The study reveals that an adversary can execute cyber-physical attacks such as sabotage and denial of service. The potential security threats emphasize the importance of implementing robust security measures to mitigate the cyber risks to computer numerical control machines.

Forihat, Yahya [Virginia Commonwealth University, ↗
DOE OSTI2026

Roadmap for Solar Photovoltaic (PV) Cybersecurity: A vision for improving cyber maturity of distributed and utility-scale solar energy installations

As the solar energy sector continues to expand, its integration into the broader energy infrastructure presents both unprecedented opportunities and new risks. The increasing reliance on digital technologies and interconnected systems in solar energy creates an expanded attack surface for motivated cyber adversaries. Cyberattacks have the potential to cause disruptions in energy production, damage to equipment, financial losses, and compromises in national security. Therefore, ensuring robust cybersecurity measures is paramount to protect the integrity, availability, confidentiality, and access control of solar energy systems. However, there are still key gaps and challenges to be addressed in industry and research, which stakeholders must race to address as they combat a growing number of real-world cyber incidents that affect solar energy systems and a growing number of vulnerabilities discovered and disclosed in key types of equipment. This roadmap explore the current state of solar PV cybersecurity and the gaps and challenges still to be addressed.

14 - SOLAR ENERGY↗
DOE OSTI2024

CO 2 storage site characterization using ensemble-based approaches with deep generative models

Estimating spatially distributed properties such as permeability from available sparse measurements is a great challenge in efficient subsurface CO 2 storage operations. In this paper, a deep generative model that can accurately capture complex subsurface structure is tested with an ensemble-based inversion method for accurate and accelerated characterization of CO 2 storage sites. We chose Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) for its realistic reservoir property representation and Ensemble Smoother with Multiple Data Assimilation (ES-MDA) for its robust data fitting and uncertainty quantification capability. WGAN-GP are trained to generate high-dimensional permeability fields from a low-dimensional latent space and ES-MDA then updates the latent variables by assimilating available measurements. Several subsurface site characterization examples including Gaussian, channelized, and fractured reservoirs are used to evaluate the accuracy and computational efficiency of the proposed method and the main features of the unknown permeability fields are characterized accurately with reliable uncertainty quantification. Furthermore, the estimation performance is compared with a widely-used variational, i.e., optimization-based, inversion approach, and the proposed approach outperforms the variational inversion method in several benchmark cases. We explain such superior performance by visualizing the objective function in the latent space: because of nonlinear and aggressive dimension reduction via generative modeling, the objective function surface becomes extremely complex while the ensemble approximation can smooth out the multi-modal surface during the minimization. This suggests that the ensemble-based approach works well over the variational approach when combined with deep generative models at the cost of forward model runs unless convergence-ensuring modifications are implemented in the variational inversion.

42 ENGINEERING↗
DOE OSTI2020

Effects of Jacobian Matrix Regularization on the Detectability of Adversarial Samples

The well-known vulnerability of Deep Neural Networks to adversarial samples has led to a rapid cycle of increasingly sophisticated attack algorithms and proposed defenses. While most contemporary defenses have been shown to be vulnerable to carefully configured attacks, methods based on gradient regularization and out-of-distribution detection have attracted much interest recently by demonstrating higher resilience to a broad range of attack algorithms. However, no study has yet investigated the effect of combining these techniques. In this paper, we consider the effect of Jacobian matrix regularization on the detectability of adversarial samples on the CIFAR-10 image benchmark dataset. We find that regularization has a significant effect on detectability, and in some cases can make an undetectable attack on a baseline model detectable. In addition, we give evidence that regularization may mitigate the known weaknesses of detectors to high-confidence adversarial samples. The defenses we consider here are highly generalizable, and we believe they will be useful for further investigations to transfer machine learning robustness to other data domains.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗