Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data privacy”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Harnessing ML Privacy by Design Through Crossbar Array Non-idealities

Deep Neural Networks (DNNs), handling computeand data-intensive tasks, often utilize accelerators like Resistiveswitching Random-access Memory (RRAM) crossbar for energyefficient in-memory computation. Despite RRAM’s inherent nonidealities causing deviations in DNN output, this study transforms the weakness into strength. By leveraging RRAM non-idealities, the research enhances privacy protection against Membership Inference Attacks (MIAs), which reveal private information from training data. RRAM non-idealities disrupt MIA features, increasing model robustness and revealing a privacy-accuracy tradeoff. Empirical results with four MIAs and DNNs trained on different datasets demonstrate significant privacy leakage reduction with a minor accuracy drop (e.g., up to 2.8% for ResNet-18 with CIFAR-100).

artificial intelligence↗
DOE OSTI2025

Securing Federated Learning Against Active Reconstruction Attacks

Federated Learning (FL) has amassed notable attention for its ability to preserve user privacy while emphasizing the retainment of model training efficiency. Due to this potential, FL has been integrated in many domains, such as healthcare, finance, law, and industrial engineering, where data cannot be easily exchanged due to sensitive information and strict privacy laws. However, current research has indicated that FL protocols are easily compromised by active data reconstruction attacks employed by actively dishonest servers. The malicious modification of global model parameters allows an actively dishonest server to obtain a direct copy of users’ private data via gradient inversion. Here, this class of attacks is highly underexplored and continues to be a major challenge due to the intense threat model. In this paper, we propose OASIS as a scalable and modality-agnostic defense based on data augmentation that counteracts active data reconstruction attacks while preserving model performance. To generalize our defense, we uncover the intuition behind gradient inversion that enables these attacks and theoretically establish the conditions by which the defense can be considered robust regardless of attack design. From this, we formulate our defense with data augmentation that illustrates its ability to undermine the attack principle. We evaluate OASIS on five real-world datasets–two image-based (ImageNet and CIFAR100) and three text-based (Wikitext, Stack Overflow, and Shakespeare)–which span diverse uses cases such as vision tasks and language modeling. Comprehensive evaluations on these datasets exhibit the efficacy of OASIS and highlight its feasibility as a solution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather

This paper leverages ongoing work in a community microgrid in Adjuntas, Puerto Rico to forecast global horizontal irradiance (GHI) and compare performance in normal and extreme weather. Given a positive correlation of 0.98 between GHI and PV power, forecasting GHI can be an effective, indirect forecast of photovoltaic (PV) power, especially in microgrids where the end-users, owners, operators, or other stakeholders are reluctant to share data for training or validation due to privacy and security concerns. A recursive one-shot (termed as "blind") forecast is, hence, formulated, wherein a gradient-boosted regression tree (GBR) is built to forecast GHI for a 7-day horizon in normal weather, and a 2-day horizon in extreme weather. To demonstrate its resilience, the architecture is trained on normal and hurricane weather GHI from 2002-2022. It is generalized on February 9-16, 2023, and on the landfall of Hurricane Nicole (Nov 4-5, 2022), respectively. Forecasts from GBR are compared against that from a satellite-based API resource and three baselines: persistence, averaging, and exponential smoothing. Results show GBR and persistence outperform sophisticated API in both types of weather for this case study.

Sundararajan, Aditya↗
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 OSTI2025

Does class matter? Understanding differential pandemic recovery via a building typology

This study investigates the recovery of building-level footfall from the COVID-19 pandemic using privacy-preserving mobile devices-based footfall data within 60 downtown areas in the USA and Canada. Using clustering, we identify five distinct building typologies based on their characteristics, including rent, quality and recovery rates. The results reveal significant variation of recovery rates by building features. We find negative relationships with footfall recovery for both the percentage of office and remote work tenants and building quality. In contrast, buildings with traditional work tenants and retail functions achieve higher recovery rates. We also test the ‘flight to quality’ hypothesis via on our typology results. High-quality office buildings (Class A+) continue to have high rents but experience low physical footfall recovery, which suggests that this class is not as resilient as portrayed. The findings thus suggest the importance of considering both economic and footfall resilience in evaluating the performance of office buildings.

Covid-19↗
NASA NTRS1982

Non-urban mobile radio market demand forecast

A national nonmetropolitan land mobile traffic model for 1990-2000 addresses user classes, density classes, traffic mix statistics, distance distribution, geographic distribution, price elasticity, and service quality elasticity. Traffic demands for business, special industrial, and police were determined on the basis of surveys in 73 randomly selected nonurban counties. The selected services represent 69% of total demand. The results were extrapolated to all services in the non-SMSA areas of the contiguous United States. Radiotelephone services were considered separately. Total non-SMSA mobile radio demand (one way) estimates are given. General functional requirements include: hand portability, privacy, reduction of blind spots, two way data transmission, position location, slow scan imagery.

Castruccio, P. A.↗
DOE OSTI2025

Differentially Private Map Matching (DPMM) v1.0

Human mobility trajectories provide valuable information for developing mobility applications, as they contain diverse and rich information about the users. User mobility data is valuable for various applications such as intelligent transportation systems (ITS), commercial business models, and disease-spread models. However, such spatio-temporal traces may pose a threat to user privacy. GPS trajectories in their raw form are not suitable for transportation studies, as they require matching locations with nearest road links — a process called map-matching. This software implements a differential privacy (DP)-based map-matching algorithm, called DPMM, that generates link-level location trajectories in a privacy-preserving manner to protect users' origin destinations (OD) and travel paths. OD privacy is achieved by injecting Planar Laplace noise to the user OD GPS points. Travel-path privacy is provided with randomized travel path construction using exponential DP mechanism. The injected noise level is selected adaptively, by considering the link density of the location and the functional category of the localized links. For path privacy, our mechanism samples waypoints and selects candidate paths between waypoints. DPMM provides privacy effectively with respect to link density instead of other trajectory samples in the database compared to other privacy mechanisms. Compared to the different baseline models our DP-based privacy model offers closer query responses to the raw data in terms of individual and aggregate trajectory-level statistics with an average at absolute deviation from the baseline for individual statistics on ϵ = 1.0. Beyond individual trajectory statistics, the DPMM outperforms the other benchmark DP-based mechanisms on different aggregate statistics with up to 8x improvement in utility.

Peisert, Sean [Lawrence Berkeley National Laborato↗
DOE OSTI2024

A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications

Graph Neural Networks (GNNs) have gained significant attention owing to their ability to handle graph-structured data and the improvement in practical applications. However, many of these models prioritize high utility performance, such as accuracy, with a lack of privacy consideration, which is a major concern in modern society where privacy attacks are rampant. To address this issue, researchers have started to develop privacy-preserving GNNs. Despite this progress, there is a lack of a comprehensive overview of the attacks and the techniques for preserving privacy in the graph domain. In this survey, we aim to address this gap by summarizing the attacks on graph data according to the targeted information, categorizing the privacy preservation techniques in GNNs, and reviewing the datasets and applications that could be used for analyzing/solving privacy issues in GNNs. We also outline potential directions for future research in order to build better privacy-preserving GNNs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Differentially Private Adaptive Noise Injection (DP-ANI) v1.0

Location data is collected from users continuously to understand their mobility patterns. Releasing the user trajectories may compromise user privacy. Therefore, the general practice is to release aggregated location datasets. However, private information may still be inferred from an aggregated version of location trajectories. Differential privacy (DP) protects the query output against inference attacks regardless of background knowledge. This software implements a differential privacy-based privacy model that protects the user's origins and destinations from being inferred from aggregated mobility datasets. This is achieved by injecting Planar Laplace noise to the user origin and destination GPS points. The noisy GPS points are then transformed into a link representation using a link-matching algorithm. Finally, the link trajectories form an aggregated mobility network. The injected noise level is selected using the Sparse Vector Mechanism. This DP selection mechanism considers the link density of the location and the functional category of the localized links. Compared to the different baseline models, including a k-anonymity method, our differential privacy-based aggregation model offers query responses that are close to the raw data in terms of aggregate statistics at both the network and trajectory-levels with maximum 9% deviation from the baseline in terms of network length.

Peisert, Sean [Lawrence Berkeley National Laborato↗
NASA NTRS2009

Human Research Program Human Health Countermeasures Element Cardiovascular Risks Standing Review Panel (SRP)

The Cardiovascular Risk Standing Review Panel (SRP) evaluated several cardiovascular risks associated with space flight along with the ongoing and emerging plans to study these issues and potentially propose and/or develop countermeasures. The areas of focus included: 1) The risk of cardiac rhythm problems during prolonged space flight, and 2) Issues related to the risk of orthostatic intolerance during re-exposure to gravity. An emerging area of concern is radiation associated vascular injury. The risk of cardiac rhythm disturbances has emerged based on case reports only. No systematic study of this risk has been published. However, concerns about this risk are heightened by the age range of astronauts, the structural changes in the heart that occur during space flight, and the potential shifts in fluids and electrolytes. The current plan is to use prolonged Holter monitor EKG records made as part of the "Integrated Cardiovascular SMO" in space to determine more about the frequency and magnitude of this problem and to link this data to complementary data from the nutrition group on electrolytes. The SRP was supportive of this approach. The SRP also felt that any data related to cardiovascular risk in space should be better coordinated with the medical screening data that all astronauts undergo at regular intervals. Additionally, while there are potential privacy issues related to this suggestion, many of the current barriers to better coordination of experimental and clinical data appear to reflect longstanding cultural traditions at NASA that need rethinking. The risk of orthostatic intolerance during re-exposure to gravity was seen by the SRP as an area supported by a wealth of published physiological evidence. The SRP also felt that moving forward with the planned approach to countermeasures was reasonable and that extensive additional hypothesis testing on the physiology of orthostatic intolerance was not needed at this time. There was support for developing ground based models of limited (e.g. 1/6 th) G environments on Earth that generated a number of ideas for consideration by NASA investigators.

Joyner, Michael↗
DOE OSTI2021

Renewable energy analysis in indigenous communities using bottom-up demand prediction

This paper provides a methodology for the holistic analysis of hybrid renewable energy systems in rural communities. Electric demand is an important component for modeling and analysis of renewable energy systems. Typically, electric demand data is not available due to the internal privacy policies of utility providers. Therefore, this study proposes the use of bottom-up approaches for the development of the electric demand profile, considering the general homogeneity of residential and commercial buildings in rural communities. As a test case, this study develops the electric demand profile and investigates the technical and environmental feasibility of a hybrid renewable energy system for the New Town community on the Fort Berthold Indian Reservation (FBIR) in North Dakota. This study conducts the hybrid renewable energy system’s analysis by developing scripts in the LK scripting language and integrating System Advisor Model software’s open-source modules for modeling of renewable energy systems. Here, the results for the validation testbed of this study show that hybrid renewable resources have higher ratios of energy used for self-consumption to the total energy generated compared to stand-alone wind and PV farms.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2023

Efforts to enhance reproducibility in a human performance research project

Background: Ensuring the validity of results from funded programs is a critical concern for agencies that sponsor biological research. In recent years, the open science movement has sought to promote reproducibility by encouraging sharing not only of finished manuscripts but also of data and code supporting their findings. While these innovations have lent support to third-party efforts to replicate calculations underlying key results in the scientific literature, fields of inquiry where privacy considerations or other sensitivities preclude the broad distribution of raw data or analysis may require a more targeted approach to promote the quality of research output. Methods: We describe efforts oriented toward this goal that were implemented in one human performance research program, Measuring Biological Aptitude, organized by the Defense Advanced Research Project Agency's Biological Technologies Office. Our team implemented a four-pronged independent verification and validation (IV&V) strategy including 1) a centralized data storage and exchange platform, 2) quality assurance and quality control (QA/QC) of data collection, 3) test and evaluation of performer models, and 4) an archival software and data repository. Results: Our IV&V plan was carried out with assistance from both the funding agency and participating teams of researchers. QA/QC of data acquisition aided in process improvement and the flagging of experimental errors. Holdout validation set tests provided an independent gauge of model performance. Conclusions: In circumstances that do not support a fully open approach to scientific criticism, standing up independent teams to cross-check and validate the results generated by primary investigators can be an important tool to promote reproducibility of results.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Generation and evaluation of synthetic patient data

Background: Machine learning (ML) has made a significant impact in medicine and cancer research; however, its impact in these areas has been undeniably slower and more limited than in other application domains. A major reason for this has been the lack of availability of patient data to the broader ML research community, in large part due to patient privacy protection concerns. High-quality, realistic, synthetic datasets can be leveraged to accelerate methodological developments in medicine. By and large, medical data is high dimensional and often categorical. These characteristics pose multiple modeling challenges. Methods: In this paper, we evaluate three classes of synthetic data generation approaches; probabilistic models, classification-based imputation models, and generative adversarial neural networks. Metrics for evaluating the quality of the generated synthetic datasets are presented and discussed. Results: While the results and discussions are broadly applicable to medical data, for demonstration purposes we generate synthetic datasets for cancer based on the publicly available cancer registry data from the Surveillance Epidemiology and End Results (SEER) program. Specifically, our cohort consists of breast, respiratory, and non-solid cancer cases diagnosed between 2010 and 2015, which includes over 360,000 individual cases. Conclusions: We discuss the trade-offs of the different methods and metrics, providing guidance on considerations for the generation and usage of medical synthetic data.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Scalable auditability of monitoring process using public ledgers

Secure auditability of monitoring processing using public ledgers that are particularly useful for monitoring surveillance orders, whereby an overseeing enforcer (“E”) checks if law enforcement agencies and companies are respectively over-requesting or over-sharing user data beyond what is permitted by the surveillance order, in a privacy-preserving way, such that E does not know the real identities of the users being surveilled, nor does E get to read the users' unencrypted data. Embodiments of the present invention also have inbuilt checks and balances to require unsealing of surveillance orders at the appropriate times, thus enabling accounting of the surveillance operation to verify that lawful procedures were followed, protecting users from government overreach, and helping law enforcement agencies and companies demonstrate that they followed the rule of law.

Panwar, Gaurav↗
DOE OSTI2021

Optimal Balance of Privacy and Utility with Differential Privacy Deep Learning Frameworks

As the number of online services has increased, the amount of sensitive data being recorded is rising. Simultaneously, the decision-making process has improved by using the vast amounts of data, where machine learning has transformed entire industries. This paper addresses the development of optimal private deep neural networks and discusses the challenges associated with this task. We focus on differential privacy implementations and finding the optimal balance between accuracy and privacy, benefits and limitations of existing libraries, and challenges of applying private machine learning models in practical applications. Our analysis shows that learning rate, and privacy budget are the key factors that impact the results, and we discuss options for these settings.

Kotevska, Olivera↗
NASA NTRSDate not supplied

Evolution of the Next Exploration Toilet through Human-in-the-Loop (HITL) Testing

Human waste collection in space is a unique and necessary function that all crewmembers must perform. The variability in how each crewmember uses the toilet to urinate and defecate introduces complexities and challenges with regards to overall hardware design. Because of this variability, it is important to consider crew inputs in all aspects of a toilet design especially with regards to crew interfaces that could impact overall waste collection. Access to crew feedback is essential to the design process and should be considered early and often through the various design phases. In 2020, NASA started a project for the Human Landing System (HLS) program to develop a Government Furnished Equipment (GFE) toilet option. The project is known as the Lavatory On-Orbit (LOO). During the early development of the LOO, the project team conducted several crew evaluations to collect and summarize valuable crew feedback on system design, function, and overall usability to influence the next design iteration. Because every person could use the system differently in space, it was extremely important to collect and analyze the data in a very methodical manner to appropriately influence the design based on the evaluation results. Establishing a standard process ensures consistent data collection from one evaluation to another, helps to maintain privacy for each test subject’s inputs and removes any potential bias from test subject to test subject. To date, the team has completed four crew evaluations on prototypes for the different LOO hardware. This paper will summarize the methodology used to conduct the evaluations as well as how data was collected and analyzed. The paper will also provide details on each of the evaluations and how the design was updated based on the results.

toilet↗
NASA NTRSDate not supplied

Evolution of the Next Exploration Toilet Through Human-in-the-Loop (HITL) Testing

Human waste collection in space is a unique and necessary function that all crewmembers must perform. The variability in how each crewmember uses the toilet to urinate and defecate introduces complexities and challenges with regards to overall hardware design. Because of this variability, it is important to consider crew inputs in all aspects of a toilet design especially with regards to crew interfaces that could impact overall waste collection. Access to crew feedback is essential to the design process and should be considered early and often through the various design phases. In 2020, NASA started a project for the Human Landing System (HLS) program to develop a Government Furnished Equipment (GFE) toilet option. The project is known as the Lavatory On-Orbit (LOO). During the early development of the LOO, the project team conducted several crew evaluations to collect and summarize valuable crew feedback on system design, function, and overall usability to influence the next design iteration. Because every person could use the system differently in space, it was extremely important to collect and analyze the data in a very methodical manner to appropriately influence the design based on the evaluation results. Establishing a standard process ensures consistent data collection from one evaluation to another, helps to maintain privacy for each test subject’s inputs and removes any potential bias from test subject to test subject. To date, the team has completed four crew evaluations on prototypes for the different LOO hardware. This paper will summarize the methodology used to conduct the evaluations as well as how data was collected and analyzed. The paper will also provide details on each of the evaluations and how the design was updated based on the results.

toilet↗