Engineering PapersSearch

SEARCH · Engineering Papers

Results for “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 55 records · Page 3

DP-TwoLevel: two-stage gradient subspace learning for differentially private federated learning

Federated learning (FL) enables collaborative model training across distributed data sources without sharing raw data, but faces fundamental challenges in communication efficiency and privacy. Differentially private (DP) training mitigates information leakage but introduces noise that degrades model performance, especially in high-dimensional settings. We propose DP-TwoLevel, a hierarchical gradient projection method that improves utility under fixed DP constraints by exploiting low-dimensional structure in model updates. Our approach learns a two-level PCA-based representation of gradients and applies DP noise in a reduced-dimensional subspace, thereby lowering the effective noise magnitude while preserving dominant signal components. We evaluate the method across three datasets (MNIST, Fashion-MNIST, CIFAR-10) and three privacy regimes (ϵ∈0.5, 1.0, 2.0). Across nine experimental settings, DP-TwoLevel consistently outperforms DP-FedAvg, achieving an average accuracy improvement of 9.44%, with larger gains observed in lower ϵ(higher-noise) regimes (up to +22.31%). We further analyze scalability across models ranging from 100K to 1.49M parameters and identify a variance-based success criterion: performance remains strong when the projection preserves more than 75% of gradient variance, degrades in a marginal regime (65–75%), and fails below this threshold. Our results demonstrate that structure-aware dimensionality reduction can significantly improve the privacy–utility tradeoff in FL without modifying formal privacy guarantees. We also provide empirical evidence of scaling limitations for global projections and motivate per-layer extensions for larger models.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)

FiberFlex: Real-time FPGA-based Intelligent and Distributed Fiber Sensor System for Pedestrian Recognition

In recent years, security monitoring of public places and critical infrastructure has heavily relied on the widespread use of cameras, raising concerns about personal privacy violations. To balance the need for effective security monitoring with the protection of personal privacy, we explore the potential of optical fiber sensors for this application. This article proposes FiberFlex, an intelligent and distributed fiber sensor system. Ultizing Field Programmable Gate Arrays (FPGA) high-level synthesis (HLS) acceleration, FiberFlex offers real-time pedestrian detection by co-designing the entire pipeline of optical signal acquisition, processing, and recognition networks based on the principles of optical fiber sensing. As a promising alternative to traditional camera-based monitoring systems, FiberFlex achieves pedestrian detection by analyzing the vibration patterns caused by pedestrian footsteps, enabling security monitoring while preserving individual privacy. FiberFlex comprises three modules: First , fiber-optic sensing system: A fiber-optic distributed acoustic sensing (DAS) system is built and used to measure the ground vibration waves generated by people walking. Second , algorithms: We first collect the training data by measuring the ground vibration waves, label the data, and use the data to train the neural network models to perform pedestrian recognition. Third , hardware accelerators: We use HLS tools to design hardware modules on FPGA for data collection and pre-processing and integrate them with the downstream neural network accelerators to perform in-line real-time pedestrian detection. The final detection results are sent back from FPGA to the host CPU. We implement our system FiberFlex with the in-house built DAS system and AMD/Xilinx Kintex7 FPGA KC705 board and verify the whole system using the real-world collected data. We conduct recognition tests on five test subjects of varying ages, heights, and weights in a fixed sensing area. Each subject experienced 20 real-time recognition tests using their daily walking habits, and the subjects were given adequate rest between tests. After 100 tests on five test subjects, the overall real-time recognition accuracy exceeded \(88.0\%\) . The whole system uses 55 W of power, 33 W in the optical DAS system and 22 W in the FPGA. Relying on its end-to-end interdisciplinary design, FiberFlex seamlessly combines fiber-optic sensors with FPGA accelerators to enable low-power real-time security monitoring without compromising privacy, making it a valuable addition to the existing security monitoring network. According to FiberFlex, more valuable research can be conducted in the future, such as fall monitoring for the elderly, migration of identification networks between different application scenarios, and improvement of anti-interference performance in more complex environments. In future perception networks, where the “eyes” are not feasible, let’s use fiber optic touch instead.

Distributed

Understanding and Modeling Pooled Rideshare Acceptance: Influential Factors, Preferred User Experiences, and Implications

This dissertation explores factors influencing pooled rideshare (PR) adoption to provide actionable insights for transportation network companies (TNCs) and policymakers. PR allows travelers to share rides with unknown passengers, offering benefits such as cost reduction and congestion relief. However, adoption remains limited due to safety concerns, privacy issues, and trust in rideshare platforms. A national U.S. survey with 5,385 respondents examined transportation preferences and barriers to PR adoption. Exploratory and confirmatory factor analyses identified five key factors influencing PR consideration—safety, service experience, privacy, traffic/environment, and time/cost. Second factor analyses examined ways to optimize PR experiences, revealing four factors—comfort/ease of use, convenience, vehicle technology/accessibility, and passenger safety. Privacy concerns, for instance, using regression analysis, were found to reduce the likelihood of PR adoption by 77%, and convenience had the potential to increase it by 156%. The Pooled Rideshare Acceptance Model (PRAM), based on the Technology Acceptance Model, assessed the impact of these factors using the Structural Equation Model (SEM). Privacy, safety, trust, and convenience had a large effect (Cohen's f2 > 0.35) on PR acceptance, while multigroup analyses (PRAMMA) explored 16 demographic variables such as gender, generation, and income, emphasizing the need for tailored strategies. Based on all the statistical analysis and workshops using descriptive statistics, 95 actionable recommendations were made from the riders' perspective. Findings highlight the importance of customized services, user experience improvements, and policy interventions to enhance PR adoption. This dissertation provides a roadmap for future research and policy development, ensuring evidence-based, practical strategies to improve PR services in the U.S. and beyond.

Gangadharaiah, Rakesh

Regression Analysis with the Directed Infusion of Data

Integrating artificial intelligence and machine learning tools into industry necessitates large-scale collaborative efforts that ensure the robust and accurate execution of downstream analytics such as time series prediction, uncertainty quantification, grid optimization, and condition monitoring. However, concerns related to data privacy pervade the nuclear industry due to the proprietary nature of its data and the possibility of data leakage. Legacy techniques such as encryption often require the explicit transmission of data to trustworthy parties, thereby inviting data leakage concerns. The ideal collaboration scenario avoids the explicit dissemination of data/code while maintaining experimental fidelity, which is currently accomplished using various techniques such as trusted execution environments, homomorphic encryption, differential privacy, and multimatrix masking. These techniques, however, often necessitate a trade-off between trust, efficiency, and utility. This article extends a previously proposed technique called the directed infusion of data (DIOD) that ensures data privacy, allows for scalable obfuscation, and combats the risk of data leakage without compromising utility. The experiments discussed in this article examine a regression-type scenario using DIOD with the goal of preserving the inferential link between two variables. Using the point-kinetics equations, regression experiments compare the performance of a model trained using the original data to that of a model trained using the obfuscated data, which produced identical results. Our claim is further strengthened by an information theoretic proof and experiment, which showed that the inferential content between variables remains the same after obfuscation, thereby avoiding the required communication of the proprietary data.

47 - OTHER INSTRUMENTATION

Dynamical Sketching for Enhanced Communication Efficiency in Federated Learning

Federated learning (FL) has revolutionized distributed machine learning by enabling collaborative model training without sharing local data. However, communication efficiency and privacy guarantees remain significant challenges. This paper introduces a dynamic sketching mechanism in FL, optimizing the trade-off between communication efficiency and model accuracy. By dynamically selecting the sketch matrix size, our approach adapts to the evolving characteristics of the data and the model, ensuring optimal performance across diverse scenarios. We leverage Bayesian optimization to systematically tune the sketch parameters, achieving an effective balance between resource efficiency and model performance. Experimental results on the MNIST dataset using a convolutional neural network (CNN) architecture validate the proposed method's efficiency and scalability. Our dynamic sketching approach significantly outperforms fixed-size sketching techniques, achieving higher compression ratios (up to 62x) and providing better privacy guarantees while maintaining high model accuracy. These findings highlight the robustness and versatility of our approach and make it a valuable solution for privacy-preserving, communication-efficient federated learning.

Afrose, Sharmin [ORNL]

Efficient Client Selection in Federated Learning

Federated Learning (FL) enables decentralized machine learning while preserving data privacy. This paper proposes a novel client selection framework that integrates differential privacy and fault tolerance. The adaptive client selection adjusts the number of clients based on performance and system constraints, with noise added to protect privacy. Evaluated on the UNSW-NB15 and ROAD datasets for network anomaly detection, the method improves accuracy by 7% and reduces training time by 25 % compared to baselines. Fault tolerance enhances robustness with minimal performance trade-offs.

Marfo, William [University of Texas at El Paso,Dep

OmniFed: A Modular Framework for Configurable Federated Learning from Edge to HPC

Federated Learning (FL) is critical for edge and High Performance Computing (HPC) where data is not centralized and privacy is crucial. We present OmniFed, a modular framework designed around decoupling and clear separation of concerns for configuration, orchestration, communication, and training logic. Its architecture supports configuration-driven prototyping and code-level override-what-you-need customization. We also support different topologies, mixed communication protocols within a single deployment, and popular training algorithms. It also offers optional privacy mechanisms including Differential Privacy (DP), Homomorphic Encryption (HE), and Secure Aggregation (SA), as well as compression strategies. These capabilities are exposed through well-defined extension points, allowing users to customize topology and orchestration, learning logic, and privacy/compression plugins, all while preserving the integrity of the core system. We evaluate multiple models and algorithms to measure various performance metrics. By unifying topology configuration, mixed-protocol communication, and pluggable modules in one stack, OmniFed streamlines FL deployment across heterogeneous environments. Github repository is available at https://github.com/at-aaims/OmniFed.

Tyagi, Sahil [ORNL] (ORCID:0009000783144745)

Barriers and Benefits: Understanding Riders’ Views on Pooled Rideshare in the U.S.

This manuscript provides actionable recommendations to enhance user satisfaction and address existing barriers regarding pooled rideshare (PR) in the United States. Despite PR’s intended benefits, such as reduced traffic congestion and cost savings, its adoption remains limited. To identify these actionable items, a U.S. nationwide survey with 5385 participants explored transportation preferences, barriers, and motivators for PR use in the summer of 2021. First, two factor analyses were conducted. The first factor analysis identified the five factors associated with one’s willingness to consider PR (time/cost, traffic/environment, safety, privacy, and service experience). The second factor analysis revealed the four factors related to ways to optimize one’s PR experience (comfort/ease of use, convenience, vehicle technology/accessibility, and passenger safety). Privacy concerns, for instance, were found to reduce the likelihood of PR adoption by 77%, and convenience had the potential to increase it by 156%. A structural equation model evaluated the relationships among these nine key factors influencing PR usage to develop the Pooled Rideshare Acceptance Model (PRAM). The privacy, safety, trust service, and convenience factors each had a significant large effect (Cohen’s f 2 > 0.35) on the model. PRAM was extended using multigroup analyses to reveal the nuanced impact of 16 demographics, including gender, generation, rideshare experience, etc., highlighting the need for tailored strategies to improve PR acceptance through the Pooled Rideshare Acceptance Model Multigroup Analyses (PRAMMAs). Multiple workshops were held with diverse audiences to translate the team’s findings to date into 84 actionable recommendations, categorized across topical areas like safety, routing, driver and passenger selection, user education, etc. These findings are a foundation for a future study to determine which items resonate with different user groups. In the meantime, the actional items serve as a user-driven resource for policymakers, transportation network companies, and researchers, offering a roadmap to potential improvements to PR services to address existing concerns with the goal of increasing the usage of PR.

actionable recommendations

Understanding and Modeling Pooled Rideshare Acceptance: Influential Factors, Preferred User Experiences, and Implications

Ridesharing allows people to share a vehicle with others traveling in the same direction, which can reduce costs and traffic congestion. Pooled rideshare (PR) services, such as UberX Share and Lyft Shared, offer an economical and environmentally friendly alternative by matching passengers traveling similar routes. However, despite these benefits, PR adoption remains low due to concerns about safety, privacy, and convenience. This research explores the factors influencing PR adoption and provides recommendations to improve user acceptance. A nationwide survey of 5,385 participants across the U.S. was conducted to understand why people choose or avoid PR. The study identified five key factors influencing PR consideration: safety, service experience, privacy, traffic/environment, and time/cost. Additional research examined ways to optimize PR experiences by identifying four critical factors: comfort/ease of use, convenience, vehicle technology/accessibility, and passenger safety. To measure the impact of these factors, a statistical model called the Pooled Rideshare Acceptance Model (PRAM) was developed, providing insights into how each element influences PR adoption. Further analysis using the Pooled Rideshare Acceptance Model Multigroup Analyses (PRAMMA) revealed how demographic characteristics such as age, gender, income, and past rideshare experience shape PR perceptions. Some key findings from the multigroup analyses showed that younger users valued technological features and environmental benefits, while older users prioritized reliability and service transparency. Additionally, privacy concerns were more significant for female users, while convenience was critical for higher-income groups. These results emphasize that a 'onesize-fits-all' approach to PR service design is not effective, highlighting the need for tailored strategies to address different user segments. Further, workshops were conducted with researchers and students to translate the findings into real-world solutions. These workshops and 3 all the statistical analyses led to the development of 95 actionable recommendations. The recommendations focus on key areas such as safety, service reliability, user education, and accessibility, offering tangible improvements to PR services. The insights from this study provide valuable guidance for policymakers, transportation network companies (TNCs), and researchers aiming to make PR services safer, more accessible, and widely accepted. By addressing user concerns, PR can become a more viable transportation option, supporting sustainable urban mobility and reducing reliance on private vehicles. Additionally, these findings emphasize the importance of user-centric service design in encouraging broader PR adoption. Future research should explore evolving trends in PR preferences, technological advancements, and policy changes to ensure continued improvements. By implementing these recommendations, PR services can better align with user expectations, enhance trust in shared mobility, and contribute to a more efficient transportation ecosystem.

29 ENERGY PLANNING, POLICY, AND ECONOMY

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

MetaHeart: Metasurface enabled biometrics camouflage

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

77 NANOSCIENCE AND NANOTECHNOLOGY

Distributed Tomographic Reconstruction with Quantization

Conventional tomographic reconstruction typically depends on centralized servers for both data storage and computation, leading to concerns about memory limitations and data privacy. Distributed reconstruction algorithms mitigate these issues by partitioning data across multiple nodes, reducing server load and enhancing privacy. However, these algorithms often encounter challenges related to memory constraints and communication overhead between nodes. In this paper, we introduce a decentralized Alternating Directions Method of Multipliers (ADMM) with configurable quantization. By distributing local objectives across nodes, our approach is highly scalable and can efficiently reconstruct images while adapting to available resources. To overcome communication bottlenecks, we propose two quantization techniques based on K-means clustering and JPEG compression. Numerical experiments with benchmark images illustrate the tradeoffs between communication efficiency, memory use, and reconstruction accuracy.

Miao, Runxuan

Automating ridehailing services would reduce pooling, especially among women

Here, this study investigates how autonomous vehicles (AVs) could transform pooled (shared) ridehailing services, focusing on the impacts of fare reductions, the absence of drivers/staff, and psychological attributes such as trust in other passengers and privacy concerns. We distinguish between the automation of driving tasks and the removal of human driver/staff from the vehicle, providing novel insights into the factors influencing AV ridehailing adoption. Using a national survey with stated preference (SP) choice experiments and psychometric questions, we analyze the complex interactions of ridehailing fare, pooled ridehailing service quality, and latent attitudes on ridehailing choices. Our findings suggest that the elimination of drivers/staff from fully autonomous ridehailing could lead to a shift from pooled to solo rides, particularly among female travelers who may have greater concerns about trust and safety in unstaffed AVs. This study highlights the importance of addressing trust and comfort beyond fare discounts to ensure the inclusivity and widespread adoption of pooled AV ridehailing. These insights underscore the need for ridehailing providers and policymakers to prioritize trust-building measures, user-centered AV design that offers greater privacy, and dynamic pricing strategies, to ensure inclusive and widespread adoption of pooled AV services.

Autonomous vehicle

Ensemble Federated Machine Learning‐Based Cybersecurity Situational Awareness in Microgrid Network

Cyber-physical microgrids are vulnerable to stealthy cybersecurity threats that disguise their actions through the exploitation of system knowledge. Such actions can severely impacts microgrids deployed in defense bases, slowing the response time of military forces during national emergencies. Several machine-learning algorithms have been proposed to detect intrusions in the grid networks; however, these traditional machine-learning algorithms lack data privacy and are subject to several adversarial machine-learning threats. This paper proposes a novel federated machine learning (FML)-based three-model framework to detect and identify stealthy data-integrity attacks while ensuring data privacy in microgrid networks. The proposed architecture uses a variational mode decomposition technique to extract derived features from incoming measurement and control datasets. The extraction of these derived features allows FML models to learn minute variations in data patterns that allow them to perform significantly better than the models trained with generic datasets consisting of raw features. Our experimental results show the efficient performance of the proposed methodology against different types of data integrity attacks while considering primary and secondary controllers in microgrids. Further, the applied FML-integrated random forest ensemble algorithm outperforms the existing generic FML algorithms during noisy and noise-free datasets with prediction latencies of only 91–134 µs per sample within the 0.1 s sampling interval and requires communication bandwidth of around ∼8.25 KB/s at the control center and ∼2.7 KB/s per edge client for communication.

24 POWER TRANSMISSION AND DISTRIBUTION

A Real-Time Implementation and Validation of Federated Learning for Grid Services

Grid-edge devices are becoming increasingly important in the energy transition. Preserving privacy was not previously considered an important aspect for power grid operations, but with the increased proliferation of customer-owned assets, it is now an essential consideration. Several mechanisms have been proposed to provide privacy for non-utility owned assets in the power grid. Federated learning (FL) is one method gaining prominence in this area. Although FL has been used for other applications, such as auto-complete in phones, there has not been much investigation into whether these approaches are feasible for grid applications. In this work, we use a research platform with real-time simulators and hardware-in-the-loop capabilities to investigate how FL can be applied to grid-edge devices, and we present the potential grid services that can be derived for these devices. We discuss the computational challenges with deploying complex FL approaches, and we explore several grid services, including participation in retail electricity markets, voltage control, and resilience-driven reconfiguration.

24 POWER TRANSMISSION AND DISTRIBUTION

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.

Wang, Jiayi [ORNL]

Scalable Federated Learning for Scientific Foundation Models on Leadership-Class Systems

Federated learning (FL) at leadership-class HPC systems remains largely unexplored, despite growing interest in deploying federated workflows on modern HPC systems. This paper provides the first system-level empirical characterization of federated fine-tuning of pretrained foundation models on an exascale supercomputer under a multi-node deployment. Using up to 96 concurrent FL clients deployed across Frontier nodes, we study the impact of client scale, model size, data heterogeneity, partial participation, and differential privacy on runtime, communication overhead, and convergence stability. Our results show that pretrained transformer models remain robust to heterogeneity, client dropout, and privacy noise, while system efficiency degrades rapidly with scale as synchronizat and orchestration dominate runtime. We further demonstrate that system-aware execution strategies, including intra-node aggregation and early aggregation, significantly reduce wall-clock time without degrading model quality. These findings establish a practical performance baseline and inform the design of communication-efficient FL systems on leadership-class HPC platforms.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)