Search NASA⌕ Search

SEARCH · Search NASA

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.

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

At least 91 records · Page 5

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↗

A total risk assessment methodology for security assessment.

Sandia National Laboratories performed a two-year Laboratory Directed Research and Development project to develop a new collaborative risk assessment method to enable decision makers to fully consider the interrelationships between threat, vulnerability, and consequence. A five-step Total Risk Assessment Methodology was developed to enable interdisciplinary collaborative risk assessment by experts from these disciplines. The objective of this process is promote effective risk management by enabling analysts to identify scenarios that are simultaneously achievable by an adversary, desirable to the adversary, and of concern to the system owner or to society. The basic steps are risk identification, collaborative scenario refinement and evaluation, scenario cohort identification and risk ranking, threat chain mitigation analysis, and residual risk assessment. The method is highly iterative, especially with regard to scenario refinement and evaluation. The Total Risk Assessment Methodology includes objective consideration of relative attack likelihood instead of subjective expert judgment. The 'probability of attack' is not computed, but the relative likelihood for each scenario is assessed through identifying and analyzing scenario cohort groups, which are groups of scenarios with comparable qualities to the scenario being analyzed at both this and other targets. Scenarios for the target under consideration and other targets are placed into cohort groups under an established ranking process that reflects the following three factors: known targeting, achievable consequences, and the resources required for an adversary to have a high likelihood of success. The development of these target cohort groups implements, mathematically, the idea that adversaries are actively choosing among possible attack scenarios and avoiding scenarios that would be significantly suboptimal to their objectives. An adversary who can choose among only a few comparable targets and scenarios (a small comparable target cohort group) is more likely to choose to attack the specific target under analysis because he perceives it to be a relatively unique attack opportunity. The opposite is also true. Thus, total risk is related to the number of targets that exist in each scenario cohort group. This paper describes the Total Risk Assessment Methodology and illustrates it through an example.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Bennett-Brassard 1984 quantum key distribution using conjugate homodyne detection

Optical homodyne detection has been widely used in continuous-variable (CV) quantum information processing for measuring field quadrature. In this paper we explore the possibility of operating a conjugate homodyne detection system in “photon counting” mode to implement discrete-variable (DV) quantum key distribution (QKD). A conjugate homodyne detection system, which consists of a beam splitter followed by two optical homodyne detectors, can simultaneously measure a pair of conjugate quadratures X and P of the incoming quantum state. In classical electrodynamics, X 2 + P 2 is proportional to the energy (the photon number) of the input light. In quantum optics, X and P do not commute and thus the above photon-number measurement is intrinsically noisy. This implies that a blind application of standard security proofs of QKD could result in pessimistic performance. We overcome this obstacle by taking advantage of two special features of the proposed detection scheme. First, the fundamental detection noise associated with vacuum fluctuations cannot be manipulated by an external adversary. Second, the ability to reconstruct the photon number distribution at the receiver's end can place additional constraints on possible attacks from the adversary. As an example, we study the security of the BB84 QKD using conjugate homodyne detection and evaluate its performance through numerical simulations. This study may open the door to a family of QKD protocols, complementary to the well-established DV-QKD based on single-photon detection and CV-QKD based on coherent detection.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

RADA

The code for regularized adversarial domain adaption is provided here. The RADA methodology is developed for correcting climate model biases using an adversarial learning strategy. The code here covers the data processing, the algorithm, the baseline models, and the evaluation.

Anderson, GemmaJ.↗

Towards Informing an Intuitive Mission Planning Interface for Autonomous Multi-Asset Teams via Image Descriptions

Establishing a basis for certification of autonomous systems using trust and trustworthiness is the focus of Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR). The Human-Machine Interface (HMI) team is working to capture and utilize the multitude of ways in which humans are already comfortable communicating mission goals and translate that into an intuitive mission planning interface. Several input/output modalities (speech/audio, typing/text, touch, and gesture) are being considered and investigated in the context human-machine teaming for the ATTRACTOR design reference mission (DRM) of Search and Rescue or (more generally) intelligence, surveillance, and reconnaissance (ISR). The first of these investigations, the Human Informed Natural-language GANs Evaluation (HINGE) data collection effort, is aimed at building an image description database to train a Generative Adversarial Network (GAN). In addition to building an image description database, the HMI team was interested if, and how, modality (spoken vs. written) affects different aspects of the image description given. The results will be analyzed to better inform the designing of an interface for mission planning.

Generative Adversarial Network (GAN)↗

Assessing Cybersecurity Resilience of Distributed Ledger Technology in Energy Sector Using the MITRE ATT&CK® ICS Framework

Digitization in the power industry enables wide connectivity among multiple new entrants such as DERs, prosumers, and P2P counterparts within or outside the Distributed Ledger Technology (DLT). The use of DLT to improve resilience in the power grid has growing support, but new technology provides new opportunities for adversaries to cause harm. This work completed by the Cybersecurity- focused task force of IEEE SA P2418.5 evaluates the potential risks by applying the MITRE ATT&CK® ICS matrix to the DLT Engineering and Cybersecurity Stack designed for power systems applications

Gourisetti, Sri Nikhil Gupta↗

Optimal Mitigation Planning For Adversarial Scenarios

We propose a generalized framework which performs an optimal partitioning of a limited budget into various organizational sectors in order to improve the cybersecurity of a smart device or component in the Cyber Physical Energy System (CPS). The framework identifies the adversarial threats and possible attack sequences which can be performed to exploit cyber vulnerabilities of the component. Thereafter, we formulate an Mixed Integer Linear Programming (MILP) optimization problem which aims to evaluate the optimal budget partitions in order to minimize the number of highly likely attack sequences. Though we provide results for using the framework in CPES, the proposed methodology can be extended for multiple domains with a set of known adversarial and mitigation actions.

Purohit, Sumit [Pacific Northwest National Laborat↗

Information-Theoretically Secure Distributed Machine Learning

A previously obscure area of cryptography known as Secure Multiparty Computation (MPC) is enjoying increased attention in the field of privacy-preserving machine learning (ML), because ML models implemented using MPC can be uniquely resistant to capture or reverse engineering by an adversary. In particular, an adversary who captures a share of a distributed MPC model provably cannot recover the model itself, nor data evaluated by the model, even by observing the model in operation. We report on our small project to survey current MPC software and judge its practicality for fielding mission-relevant distributed machine learning models.

97 MATHEMATICS AND COMPUTING↗

The Double-edged Sword of Data-driven Super-Resolution: Adversarial Super-resolution Models

Data-driven super-resolution (SR) methods are often integrated into imaging pipelines as preprocessing steps to improve downstream tasks such as classification and detection. However, these SR models introduce a previously unexplored attack surface into imaging pipelines. In this paper, we present AdvSR, a framework demonstrating that adversarial behavior can be embedded directly into SR model weights during training, requiring no access to inputs at inference time. Unlike prior attacks that perturb inputs or rely on backdoor triggers, AdvSR operates entirely at the model level. By jointly optimizing for reconstruction quality and targeted adversarial outcomes, AdvSR produces models that appear benign under standard image quality metrics while inducing downstream misclassification. We evaluate AdvSR on three SR architectures (SRCNN, EDSR, SwinIR) paired with a YOLOv11 classifier and demonstrate that AdvSR models can achieve high attack success rates with minimal quality degradation. These findings highlight a new model-level threat for imaging pipelines, with implications for how practitioners source and validate models in safety-critical applications.

Sullivan, Haley [ORNL] (ORCID:0000000274069217)↗

SECURITY MODELING FOR MARITIME PORT DEFENSE RESOURCE ALLOCATION

Redeployment of existing law enforcement resources and optimal use of geographic terrain are examined for countering the threat of a maritime based small-vessel radiological or nuclear attack. The evaluation was based on modeling conducted by the Savannah River National Laboratory that involved the development of options for defensive resource allocation that can reduce the risk of a maritime based radiological or nuclear threat. A diverse range of potential attack scenarios has been assessed. As a result of identifying vulnerable pathways, effective countermeasures can be deployed using current resources. The modeling involved the use of the Automated Vulnerability Evaluation for Risks of Terrorism (AVERT{reg_sign}) software to conduct computer based simulation modeling. The models provided estimates for the probability of encountering an adversary based on allocated resources including response boats, patrol boats and helicopters over various environmental conditions including day, night, rough seas and various traffic flow rates.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Adversarial autoencoder ensemble for fast and probabilistic reconstructions of few-shot photon correlation functions for solid-state quantum emitters

Second-order photon correlation measurements [g (2) (τ) functions] are widely used to classify single-photon emission purity in quantum emitters or to measure the multiexciton quantum yield of emitters that can simultaneously host multiple excitations – such as quantum dots – by evaluating the value of g (2) (τ = 0). Accumulating enough photons to accurately calculate this value is time consuming and could be accelerated by fitting of few-shot photon correlations. Here, we develop an uncertainty-aware, deep adversarial autoencoder ensemble (AAE) that reconstructs noise-free g (2) (τ) functions from noise-dominated, few-shot inputs. The model is trained with simulated g (2) (τ) functions that are facilely generated by Poisson sampling time bins. The AAE reconstructions are performed orders-of-magnitude faster, with reconstruction errors and estimates of g (2) (τ = 0) that are lower in variance and similar in accuracy compared to Maximum likelihood estimation and Levenberg-Marquardt least-squares fitting approaches, for simulated and experimentally measured few-shot g (2) (τ) functions (~100 two-photon events) of InP/ZnS/ZnSe and CdS/CdSe/CdS quantum dots. The deep-ensemble model comprises eight individual autoencoders, allowing for probabilistic reconstructions of noise-free g (2) (τ) functions, and we show that the predicted variance scales inversely with number of shots, with comparable uncertainties to computationally intensive Markov chain Monte Carlo sampling. Furthermore, this work demonstrates the advantage of machine learning models to perform uncertainty-aware, fast, and accurate reconstructions of simple Poisson-distributed photon correlation functions, allowing for on-the-fly reconstructions and accelerated materials characterization of solid-state quantum emitters.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

A complexity science-based framework for global joint operations analysis to support force projection: LDRD Final Report

The military is undergoing a significant transformation as it modernizes for the information age and adapts to address an emerging asymmetric threat beyond traditional cold war era adversaries. Techniques such as traditional large-scale, joint services war gaming analysis are no longer adequate to support program evaluation activities and mission planning analysis at the enterprise level because the operating environment is evolving too quickly. New analytical capabilities are necessary to address modernization of the Department of Defense (DoD) enterprise. This presents significant opportunity to Sandia in supporting the nation at this transformational enterprise scale. Although Sandia has significant experience with engineering system of systems (SoS) and Complex Adaptive System of Systems (CASoS), significant fundamental research is required to develop modeling, simulation and analysis capabilities at the enterprise scale. This report documents an enterprise modeling framework which will enable senior level decision makers to better understand their enterprise and required future investments.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Security Evaluation of Smart Cards and Secure Tokens: Benefits and Drawbacks for Reducing Supply Chain Risks of Nuclear Power Plants

The supply chain attack pathway is being increasingly used by adversaries to bypass security controls and gain unauthorized access to sensitive networks and equipment (e.g., Critical Digital Assets). Cyber-attacks targeting supply chain generally aim to compromise the environments, products, or services of vendors and suppliers to inject, add, or substitute authentic software and hardware with malicious elements. These malicious elements are deemed to be authentic as they arise from the vendor or supplier (i.e., the supply chain). This research aims to leverage findings and assumptions made from the previous report to determine the security benefits and drawbacks of a smart card- based hardware root of trust. Smart cards can provide devices inside Nuclear Power Plants (NPP) with a secure environment to store keys in and perform sensitive operations such as digital signature generation. These abilities can be leveraged to increase supply chain cybersecurity by autonomously providing NPP Licensees with reports on device integrity, authenticity and measurements of executable and non-executable data.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Diagnosing autonomous vehicle driving criteria with an adversarial evolutionary algorithm

We repurposed an adversarial evolutionary algorithm, Gremlin, from finding driving scenarios where a model of an autonomous vehicle drove poorly to troubleshooting driving quality evaluation criteria. We evaluated the driving performance of a "perfect driver" robot in a virtual town environment using the same fitness criteria intended for a deep learner (DL) trained driver. We found that the fitness evaluation criteria poorly handled turns, and used Gremlin to iteratively improve that criteria. We were confident that the same criteria could then be applied to the DL-based models as originally intended, and that this approach could be used as a general means of troubleshooting autonomous vehicle driving criteria.

Coletti, Mark↗

Generative Adversarial Network for Synthetic Time Series Data Generation in Smart Grids

The availability of fine grained time series data is a pre-requisite for research in smart-grids. While data for transmission systems is relatively easily obtainable, issues related to data collection, security and privacy hinder the widespread public availability/accessibility of such datasets at the distribution system level. This has prevented the larger research community from effectively applying sophisticated machine learning algorithms to significantly improve the distribution-level accuracy of predictions and increase the efficiency of grid operations. Synthetic dataset generation has proven to be a promising solution for addressing data availability issues in various domains such as computer vision, natural language processing and medicine. However, its exploration in the smart grid context remains unsatisfactory. Previous works have tried to generate synthetic datasets by modeling the underlying system dynamics: an approach which is difficult, time consuming, error prone and often times infeasible in many problems. In this work, we propose a novel data-driven approach to synthetic dataset generation by utilizing deep generative adversarial networks (GAN) to learn the conditional probability distribution of essential features in the real dataset and generate samples based on the learned distribution. To evaluate our synthetically generated dataset, we measure the maximum mean discrepancy (MMD) between real and synthetic datasets as probability distributions, and show that their sampling distance converges. To further validate our synthetic dataset, we perform common smart grid tasks such as k-means clustering and short-term prediction on both datasets. Experimental results show the efficacy of our synthetic dataset approach: the real and synthetic datasets are indistinguishable by solely examining the output of these tasks.

14 SOLAR ENERGY↗

Adaptive Stress Testing of Trajectory Predictions in Flight Management Systems

To find failure events and their likelihoods in flight-critical systems, we investigate the use of an advanced black-box stress testing approach called adaptive stress testing. We analyze a trajectory predictor from a developmental commercial flight management system which takes as input a collection of lateral waypoints and en-route environmental conditions. Our aim is to search for failure events relating to inconsistencies in the predicted lateral trajectories. The intention of this work is to find likely failures and report them back to the developers so they can address and potentially resolve shortcomings of the system before deployment. To improve search performance, this work extends the adaptive stress testing formulation to be applied more generally to sequential decision-making problems with episodic reward by collecting the state transitions during the search and evaluating at the end of the simulated rollout. We use a modified Monte Carlo tree search algorithm with progressive widening as our adversarial reinforcement learner. The performance is compared to direct Monte Carlo simulations and to the cross-entropy method as an alternative importance sampling baseline. The goal is to find potential problems otherwise not found by traditional requirements-based testing. Results indicate that our adaptive stress testing approach finds more failures and finds failures with higher likelihood relative to the baseline approaches.

adaptive stress testing↗

Model Assumptions and Data Characteristics: Impacts on Domain Adaptation in Building Segmentation

Studies on domain adaptation (DA) for remote sensing (RS) imagery analysis lack consistency in selection and description of evaluation scenarios. Without properly characterizing datasets, model assumptions, and evaluation scenarios, it is difficult to objectively compare DA methods and reach conclusions about their suitability across different applications. With this motivation, this work seeks to empirically assess to which extent the interaction between data characteristics and model assumptions influences the effectiveness of DA methods. Using the widely explored task of building footprint segmentation as a case study, we perform a large-scale study across over 200 DA scenarios that include variations across view angles, areas observed, and sensors used for data acquisition. Rather than adopting different model architectures or optimization criteria, we contrast the performances of two DA methods based on adversarial learning that differ only in their assumptions about source and target domains. Informed by metadata and data characteristics unveiled using traditional computer vision (CV) techniques as well as pretrained deep models, we provide a detailed meta-analysis of experiments highlighting the importance of accurately considering data assumptions for DA in RS segmentation tasks. As demonstrated by a “cherry-picking” exercise, different claims regarding which model is best could be made by selecting different subsets of evaluation scenarios. While well-calibrated assumptions can be beneficial, mismatching assumptions can lead to negative biases in DA applications. Furthermore, this study intends to motivate the community toward more consistent evaluation protocols while providing recommendations and insights toward creating novel benchmark datasets, documenting data characteristics, application-specific knowledge, and model assumptions.

42 ENGINEERING↗

RanCompute: Computational Security in Embedded Devices via Random Input and Output Encodings

An embedded device in an insecure environment is subject to additional security risk through capture and reverse-engineering by a capable adversary. If this device contains a microchip performing sensitive computations, capture of the chip may leak functionality to an adversary. In this paper we propose a novel method in which we randomly encode the input operands and the outputs of a computation, thus not revealing the arithmetic operations being performed. The operations are sequenced in a graph representing the overall application. Once the initialization values are overwritten and lost, the results of these computations are indecipherable by the device performing the calculations as well as by any adversary. The result is transmitted back to a secure server which has stored the initialization values and so can decode the results which appear random to the adversary.

Embedded computing↗