SEARCH · Engineering Papers

Results for “adversarial evaluation”

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.

SourceResearch connectionFrom yearThrough year

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

At least 109 records · Page 6

All sources NASA NTRS DOE OSTI

DOE OSTI2020

Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of an ML model, whereas backdoor data poisoning attacks maintain system performance unless the MLmodel is presented with an input containing an embedded“trigger” that provides a predetermined response advantageous to the adversary. Our work builds upon prior back-door data-poisoning research for ML image classifiers and systematically assesses different experimental conditions including types of trigger patterns, persistence of trigger patterns during retraining, poisoning strategies, architectures (ResNet-50, NasNet, NasNet-Mobile), datasets (Flowers, CIFAR-10), and potential defensive regularization techniques (Contrastive Loss, Logit Squeezing, Manifold Mixup,Soft-Nearest-Neighbors Loss). Experiments yield four key findings. First, the success rate of backdoor poisoning at-tacks varies widely, depending on several factors, including model architecture, trigger pattern and regularization technique. Second, we find that poisoned models are hard to detect through performance inspection alone. Third, regularization typically reduces backdoor success rate, although it can have no effect or even slightly increase it, depending on the form of regularization. Finally, backdoors inserted through data poisoning can be rendered ineffective after just a few epochs of additional training on a small set of clean data without affecting the model’s performance.

Truong, Loc T.↗

DOE OSTI2023

Parameters, Properties, and Process: Conditional Neural Generation of Realistic SEM Imagery Toward ML-Assisted Advanced Manufacturing

Abstract The research and development cycle of advanced manufacturing processes traditionally requires a large investment of time and resources. Experiments can be expensive and are hence conducted on relatively small scales. This poses problems for typically data-hungry machine learning tools which could otherwise expedite the development cycle. We build upon prior work by applying conditional generative adversarial networks (GANs) to scanning electron microscope (SEM) imagery from an emerging advanced manufacturing process, shear-assisted processing and extrusion (ShAPE). We generate realistic images conditioned on temper and either experimental parameters or material properties. In doing so, we are able to integrate machine learning into the development cycle, by allowing a user to immediately visualize the microstructure that would arise from particular process parameters or properties. This work forms a technical backbone for a fundamentally new approach for understanding manufacturing processes in the absence of first-principle models. By characterizing microstructure from a topological perspective, we are able to evaluate our models’ ability to capture the breadth and diversity of experimental scanning electron microscope (SEM) samples. Our method is successful in capturing the visual and general microstructural features arising from the considered process, with analysis highlighting directions to further improve the topological realism of our synthetic imagery.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Security Self-Assessment Toolkit for Nuclear Materials Facilities: Focus on Insider Threat Mitigation

Theft or sabotage of weapons-usable nuclear materials is a global concern. To minimize this threat, establishing and maintaining an effective nuclear security regime is required to protect against criminal or other negligent acts. Use of a formalized insider threat mitigation program is one such security measure. Individuals who have or held authorized access to an organization's critical assets, such as nuclear materials, are considered "insiders." Insider threats, or insider adversaries, are motivated individuals who possess access, authority, and knowledge to conduct a malicious act or facilitate that of an external party. To thwart insider threats (both intentional and unintentional), organizations can formalize an enterprise-wide approach to identify and mitigate the unique risks presented by insiders. This report provides an approach to evaluate an insider threat mitigation program at facilities with nuclear materials. Formal program evaluations serve many purposes and can be designed using several different methods and techniques. This report presents a self-assessment approach to program evaluation whereby an organization can assess its strengths, identify key gaps, and set priorities for ongoing improvement efforts to mitigate insider threats. Results of the self-assessment can provide critical information to contribute to the continuous improvement of an organization’s insider threat mitigation program within eight specific domain areas.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

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 OSTI2022

BioADAPT-MRC: adversarial learning-based domain adaptation improves biomedical machine reading comprehension task

ABSTRACT Motivation Biomedical machine reading comprehension (biomedical-MRC) aims to comprehend complex biomedical narratives and assist healthcare professionals in retrieving information from them. The high performance of modern neural network-based MRC systems depends on high-quality, large-scale, human-annotated training datasets. In the biomedical domain, a crucial challenge in creating such datasets is the requirement for domain knowledge, inducing the scarcity of labeled data and the need for transfer learning from the labeled general-purpose (source) domain to the biomedical (target) domain. However, there is a discrepancy in marginal distributions between the general-purpose and biomedical domains due to the variances in topics. Therefore, direct-transferring of learned representations from a model trained on a general-purpose domain to the biomedical domain can hurt the model’s performance. Results We present an adversarial learning-based domain adaptation framework for the biomedical machine reading comprehension task (BioADAPT-MRC), a neural network-based method to address the discrepancies in the marginal distributions between the general and biomedical domain datasets. BioADAPT-MRC relaxes the need for generating pseudo labels for training a well-performing biomedical-MRC model. We extensively evaluate the performance of BioADAPT-MRC by comparing it with the best existing methods on three widely used benchmark biomedical-MRC datasets—BioASQ-7b, BioASQ-8b and BioASQ-9b. Our results suggest that without using any synthetic or human-annotated data from the biomedical domain, BioADAPT-MRC can achieve state-of-the-art performance on these datasets. Availability and implementation BioADAPT-MRC is freely available as an open-source project at https://github.com/mmahbub/BioADAPT-MRC. Supplementary information Supplementary data are available at Bioinformatics online.

60 APPLIED LIFE SCIENCES↗

NASA NTRS1993

Assessment of Russian VSTOL technology evaluating the YAK-38 'FORGER' and YAK-141 'FREESTYLE'

The dissolution of the Former Soviet Union (FSU) created new relationships between the world superpowers. Overnight, the Commonwealth of Independent States (CIS), formed from the remnants of the FSU, began the difficult transformation to a free market society. Military hardware that had once been highly classified and the basis for our own defense planning was now openly marketed at airshows around the world. 'Test' flights were available for potential customers and cooperative partnerships were explored between former adversaries. This environment permitted a visit to the Yakovlev Design Bureau, (YAK) for a vertical/short takeoff and landing (VSTOL) technology assessment. Yakovlev is the FSU's sole Design Bureau with experience in VSTOL aircraft and has developed two flying examples, the YAK-38 'FORGER' and YAK-141 'FREESTYLE'. This article reviews the performance of the YAK-38 'FORGER' and the YAK-141 'FREESTYLE'.

Nalls, Art↗

DOE OSTI2026

Robust Explanations using Diverse Adversarially Trained Ensembles, Multi-Modal Contrastive Learning, and Attribution-based Confidence Metrics

The primary objective of this project is to strengthen the trustworthiness of AI systems by designing algorithms that make their internal decision-making processes more understandable to human users. This involves creating clear, interpretable explanations for AI decisions and developing metrics to assess these explanations' validity and reliability. Significant progress has been achieved through (i) developing symbolic explanations, (ii) generating meaningful interpretive insights, (iii) establishing accuracy and confidence metrics, and (iv) devising methods to evaluate the knowledge boundaries of AI models. To date, the research findings have been shared in peer-reviewed publications, with accompanying scientific and technical information (STI) detailed below.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2019

A Communication Channel Density Estimating Generative Adversarial Network

Autoencoder-based communication systems use neural network channel models to backwardly propagate message reconstruction error gradients across an approximation of the physical communication channel. In this work, we develop and test a new generative adversarial network (GAN) architecture for the purpose of training a stochastic channel approximating neural network. In previous research, investigators have focused on additive white Gaussian noise (AWGN) channels and/or simplified Rayleigh fading channels, both of which are linear and have well defined analytic solutions. Given that training a neural network is computationally expensive, channel approximation networks— and more generally the autoencoder systems—should be evaluated in communication environments that are traditionally difficult. To that end, our investigation focuses on channels that contain a combination of non-linear amplifier distortion, pulse shape filtering, intersymbol interference, frequency-dependent group delay, multipath, and non-Gaussian statistics. Each of our models are trained without any prior knowledge of the channel. We show that the trained models have learned to generalize over an arbitrary amplifier drive level and constellation alphabet. We demonstrate the versatility of our GAN architecture by comparing the marginal probability density function of several channel simulations with that of their corresponding neural network approximations

Smith, Aaron↗

DOE OSTI2023

Complete Evaluation on Advanced Reactor Machine Learning Subversion Attacks (Final)

Navigating through the world of Artificial Intelligence (AI) in nuclear reactors and their Instrumentation and Control (I&C) systems demands a careful, deliberate journey. AI’s capability to manage massive datasets and streamline control systems has indeed carved out a significant role in various sectors, including nuclear energy. However, while AI, and particularly Large Language Models (LLMs), bring a lot to the table in terms of operational efficiency and anomaly detection, they also expose the sector to a new breed of cybersecurity threats, like Inference Attacks, Adversarial Attacks, and Trojan Attacks. This guide is designed to be a straightforward manual, diving deep into the intertwining worlds of AI and cybersecurity within nuclear reactors, and tailoring insights for three crucial audiences: I&C Vendors/Developers, Nuclear Regulators, and Nuclear Reactor Operators and Cyber Defense Teams. (1) Section 2, directed at I&C Vendors/Developers, will provide a clear and focused look at several cybersecurity attacks, offering practical recommendations and detailed scenarios related to AI cybersecurity. This section isn’t just about identifying problems but also about giving solid, usable solutions. (2) Section 3, meant for Nuclear Regulators, gets straight to the point about regulations, policy suggestions, and guidelines that are needed to lay down a robust, secure, and ethical foundation for the application of AI in nuclear operations. The focus is on making sure that everything adheres to international standards and laws while being practicable and clear-cut. (3) Section 4, aimed at Nuclear Reactor Operators and Cyber Defense Teams, offers an exhaustive exploration and technical reports, with clear recommendations and scenario analyses vital to protect operational environments and guarantee the secure application of AI in nuclear reactor operations. The goal is simple: as we step into an era where AI becomes a fundamental element of our technological and energy infrastructures, this guide is here to act as a clear, direct handbook, ensuring that AI is implemented within the nuclear sector in a manner that is secure, responsible, and practical. It’s about striking a balance – optimizing the undeniable benefits offered by AI while securing and shielding against potential cyber threats as we move through this new and complex landscape.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2023

MultiLoad-GAN: A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations

This paper presents a deep-learning framework, Multi-load Generative Adversarial Network (MultiLoad-GAN), for generating a group of synthetic load profiles (SLPs) simultaneously. The main contribution of MultiLoad-GAN is the capture of spatial-temporal correlations among a group of loads that are served by the same distribution transformer. This enables the generation of a large amount of correlated SLPs required for microgrid and distribution system studies. Here, the novelty and uniqueness of the MultiLoad-GAN framework are three-fold. First, to the best of our knowledge, this is the first method for generating a group of load profiles bearing realistic spatial- temporal correlations simultaneously. Second, two complementary realisticness metrics for evaluating generated load profiles are developed: computing statistics based on domain knowledge and comparing high-level features via a deep-learning classifier. Third, to tackle data scarcity, a novel iterative data augmentation mechanism is developed to generate training samples for enhancing the training of both the classifier and the MultiLoad-GAN model. Simulation results show that MultiLoad- GAN can generate more realistic load profiles than existing approaches, especially in group level characteristics. With little finetuning, MultiLoad-GAN can be readily extended to generate a group of load or PV profiles for a feeder or a service area.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2020

Cyber-physical Architecture For Automated Responses (cyphar) In Adversarial Ot Environments

The ability to react to a malicious attack starts with high fidelity recognition, and with that, an agile response to the attack. The current operational technology (OT) systems for a critical infrastructure may include an intrusion detection system (IDS), but the ability to adapt to an intrusion is a human initiated response. Orchestrators, which are coming of age in the financial sector and allow for levels of automated response, are not prevalent in the OT space. To evolve to such responses in the OT space, a tradeoff analysis is first needed, The tradeoff analysis, which evaluates the mitigation benefits of responses versus the physical affects that result, inform an automated response decision. The intent of this paper is to provide a formulation of a tradeoff analysis and its use in advancing automated, agile responses.

Rieger, CraigG.↗

DOE OSTI2022

Transactional Knowledge Graph Generation To Model Adversarial Activities

A Knowledge Graph (KG) is a formal and structured representation of facts, relationships, and semantic descriptions of a set of entities. Traditionally, KGs are used to describe metadata about entities and to provide additional context to target application results. Many real-world domains also involve temporal interactions between entities in addition to the metadata data. Modeling these attributed transactions is a critical requirement when using KGs in complex real-world applications. Modeling adversarial activities is one such application that develops methodology and tools to produce realistic large-scale background activity graphs that include embedded Weapons of Mass Destruction (WMD) activity patterns. We present a novel platform for constructing a transactional knowledge graph from a diverse set of sources. We present the core components and architecture of the framework, and a use case for generating a background knowledge graph and WMD activity template to evaluate network alignment and subgraph matching algorithms.

Purohit, Sumit↗

DOE OSTI2020

Anomaly Detection and Mitigation for Wide-Area Damping Control using Machine Learning

In an interconnected multi-area power system, wide-area measurement based damping controllers are used to damp out inter-area oscillations, which jeopardize grid stability and constrain the power flows below to their transmission capacity. The effect of wide-area damping control (WADC) significantly depends on both power and cyber systems. At the cyber system layer, an adversary can inflict the WADC process by compromising either measurement signals, control signals or both. Stealthy and coordinated cyber-attacks may bypass the conventional cybersecurity measures to disrupt the seamless operation of WADC. This paper proposes an anomaly detection (AD) algorithm using supervised Machine Learning and a model-based logic for mitigation. The proposed AD algorithm considers measurement signals (input of WADC) and control signals (output of WADC) as input to evaluate the type of activity such as normal, perturbation (small or large signal faults), attack and perturbation-and-attack. Upon anomaly detection, the mitigation module tunes the WADC signal and sets the control status mode as either wide-area mode or local mode. The proposed anomaly detection and mitigation (ADM) module works inline with the WADC at the control center for attack detection on both measurement and control signals and eliminates the need for ADMs at the geographically distributed actuators. Here, we consider coordinated and primitive data-integrity attack vectors such as pulse, ramp, relay-trip and replay attacks. The performance of the proposed ADM algorithms was evaluated under these attack vector scenarios on a testbed environment for 2-area 4-machine power system. The ADM module shows effective performance with 96:5% accuracy to detect anomalies.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

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 OSTI2020

Autonomous Tools for Attack Surface Reduction

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2021

Autonomous Tools for Attack Surface Reduction (Final Report)

The electric power grid is a complex critical infrastructure that forms the lifeline of modern society, and its secure and reliable operation is of paramount importance to national security and economic wellbeing. However, recent findings documented in authoritative sources indicate the threat of cyber-based attacks growing in numbers and sophistication. However, securing the grid against stealthy cyberattacks is a challenging task due to legacy nature of the infrastructure coupled with dynamic nature of threat landscape and ever-growing sophistication of the adversaries. Additionally, the grid’s attack surface continues to grow with the increased dependence on digital communications and control that now extends to each consumer through smart meters and distributed energy resources. Unfortunately, this expansive surface increases the grid’s vulnerability and further exposes critical control systems in both substations and control centers. To respond to this emerging need, we had successfully assembled an interdisciplinary team with academic- industry partnership to successfully conduct research, development, evaluation, demonstration, and commercialization of attack surface reduction tools, whose goal was to significantly reduce the cyber attack surface in the North American power grid. Our proposed project was a synergistic collaborative effort leveraging the synergistic expertise of the team members across power systems, cyber security and CPS security, testbeds, field deployments and demonstration, and successful commercialization. The following are the specific tasks that have been successfully completed two phases (2016-2020). Phase I: Task 1: Developed and implemented a robust Project Management and Data Management Plan, coupled with a well thought out Risk Mitigation Plan. Task 2.1: Developed a comprehensive framework that continually assesses and autonomously reduces the attack surface for the power grid control environment spanning across substations, control center and the SCADA network to significantly reduce the risks of cyber attacks. Task 2.2: Developed attack surface analysis techniques, metrics, and tools that assess the attack surface at multiple levels including the control center, substations, and the SCADA network. Task 2.3: Developed attack surface reduction techniques and tools that dynamically reduce attack surface and hence increase attacker’s cost without interfering in the critical functions of the system. Task 2.4: Prototyped, implemented, and quantitatively evaluated/validated the techniques and tools on a realistic industrial CPS security testbed environment by leveraging the unique resources of the team. Task 3: Developed Commercialization plan to transition the developed tools into power system industry stakeholders for a broader adoption by leveraging the expertise of our industrial members. Phase II: Task 4: Successfully completed field demonstration, verification, and evaluation of the effectiveness of the attack surface analysis and reduction techniques on a realistic utility testbed environment. This also involved the development of realistic scenarios, sound metrics, data sets, evaluation criteria, and documentation. Technology integration & Field demonstration: The project had significantly advanced the state-of-the-art research and practice in improving the cybersecurity of our nation’s power grid infrastructure against cyber threats. In particular, the proposed, designed, and deployed attack surface analysis and reduction algorithms and tools have contributed to significantly reducing the exposure and risk of the devices, substations, and the integrated SCADA/EMS/ DMS grid environment to cyber threat. Strong demonstration and evaluation techniques have verified the feasibility of the developed techniques on realistic cyber-physical testbeds and utility partner's real grid environment, and collaborative research and evaluation of attack surface reduction techniques (for wide-are monitoring and control) within a vendor (GE) EMS platform. The Attack Host Analyzer (AHA) tool that was developed through this project was made available through GitHub.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

Deep generative models for vehicle speed trajectories

Generating realistic vehicle speed trajectories is a crucial component in evaluating vehicle fuel economy and in predictive control of self-driving cars. Traditional generative models rely on Markov chain methods and can produce accurate synthetic trajectories but are subject to the curse of dimensionality. They do not allow to include conditional input variables into the generation process. In this paper, we show how extensions to deep generative models allow accurate and scalable generation. Proposed architectures involve recurrent and feed-forward layers and are trained using adversarial techniques. Our models are shown to perform well on generating vehicle trajectories using a model trained on GPS data from Chicago metropolitan area.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2023

Digital Engineering and Cybersecurity Decision Analysis in Early Phases of SMR-Driven IES Projects

Considerable efforts are underway to ensure cybersecurity is integrated into the systems engineering lifecycle. Cyber-informed engineering and security-by-design frameworks are intended to identify and engineer out cybersecurity risks throughout the lifecycle. While these approaches are valuable for promoting the need to include cybersecurity considerations in early design phases to create more secure systems, they may not consider the entirety of digital risks. Digital risks in a digital instrumentation and control system include adversarial and unintentional risks from internal and external factors, such as human performance errors, design flaws, environmental conditions, and equipment degradation or failure. This report provides a detailed discussion on digital risk prior to describing the background and concept of operations for a small modular reactor-driven integrated energy system connected to industrial applications. The challenges of competing objectives and competing stakeholder requirements are discussed and the impacts on digital engineering, security considerations, and interdependencies are evaluated for mission-level, facility-level, and system-level decisions.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗