SEARCH · Engineering Papers

Results for “COMPARATIVE EVALUATIONS”

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 181 records · Page 10

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Tunable structure and reinforcement of polyvinyl alcohol (PVA) hydrogels using fungal chitin particles

Polysaccharides, including chitin, are one of the most abundant biopolymers in nature and are increasingly recognized as a sustainable alternative to petroleum-derived plastics and synthetic fillers in polymer composites. Traditionally sourced from crustacean shells, chitin offers mechanical strength and biocompatibility with limitations also in processability and functionality. Fungal-derived chitin material represents a promising alternative, with advantages including scalable fermentation on low-cost substrates, absence of shellfish allergens, and tunable molecular architectures that vary by species, developmental stage, and growth environment. Here, in this study, we systematically examined chitinous materials obtained from taxonomically and functionally distinct fungi, Laccaria bicolor, Trichoderma reesei and Rhizopus oryzae, to assess their structural, chemical, and morphological properties as reinforcement agents in polymer composites. Mild alkaline pretreatment was employed to obtain mycelium chitin particles, thereby improving accessibility to chitin and co-occurring β-D-glucans while maintaining microparticle integrity. Comprehensive FTIR and solid-state NMR analyses revealed species-specific differences in chemical composition and microstructure, with R. oryzae exhibiting a unique spectral signature. These fungal-derived chitin were then incorporated into poly(vinyl alcohol) (PVA) hydrogels, where they acted as reinforcing fillers without the need for additional chemical crosslinkers. Comparative evaluation of hydrogel properties demonstrated that fungal chitin significantly enhanced mechanical performance, with all mycelium fillers mitigating the water weakening in PVA hydrogels. R. oryzae-derived composites tripled the hydrogel tensile strength while the submicron fibrous morphology in L. bicolor contributes to over 45 % tensile improvement in dry PVA composites. Our findings highlight the potential of fungal biomass as a tunable, sustainable platform for producing chitin-based reinforcing agents.

Chitin↗

DOE OSTI2022

DECOVALEX-2019: An international collaboration for advancing the understanding and modeling of coupled thermo-hydro-mechanical-chemical (THMC) processes in geological systems

The DECOVALEX Project is an international research collaboration for advancing the understanding and modeling of coupled thermo-hydro-mechanical-chemical (THMC) processes in geological systems. DECOVALEX stands for “DEvelopment of COupled Models and VALidation against EXperiments”. The creation of this international initiative, now running for almost 30 years, was motivated by the recognition that prediction of these coupled effects is an essential part of the performance and safety assessment of geologic disposal systems for radioactive waste and spent nuclear fuel, and also for a range of other sub-surface engineering activities. DECOVALEX emphasizes joint analysis and comparative modeling of state-of-the-art field and laboratory experiments, across a range of host rock options and repository designs. Participating research teams are from radioactive waste management organizations, national research institutes, regulatory agencies, universities, and consulting groups, providing a wide range of perspectives and solutions to these complex problems. The most recent phase of the DECOVALEX Project, here referred to as DECOVALEX-2019, started in 2016 and ended in 2019. Modeling teams from 13 international partner organizations participated in the comparative evaluation of seven modeling tasks involving complex field and/or laboratory experiments. Furthermore, this Virtual Special Issue on DECOVALEX-2019 provides an in-depth overview of these collaborative research efforts and how these have advanced the state-of-the-art of understanding and modeling coupled THMC processes.

58 GEOSCIENCES↗

DOE OSTI2025

Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field ($B^{+}_{1}$) inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate $B^{+}_{1}$ inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000 × speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel $B^{+}_{1}$ fields. Next, we train a Residual Network (ResNet) to map $B^{+}_{1}$ fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.

Deep learning↗

DOE OSTI2021

Chorioallantoic membrane vascularization. A meta-analysis

The CAM is a widely used experimental assay to study angiogenesis, wound healing, tumor growth and metastatic process. In this study, we have analyzed and compared the existent literature data concerning the growth of the CAM. Moreover, we have analyzed the data concerning the development of the vascular system and the expression of the most important pro-angiogenic and anti-angiogenic factors. The availability of these data and their comparative evaluation allow to better analyze the experimental data concerning the testing of different pro-angiogenic and anti-angiogenic molecules, as well as biomaterials in the CAM assay. Moreover, the dynamic of the angiogenic response to different tumor cell lines and or tumor bioptic specimens, may be also better evaluated and estimated.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

Role of Metal Cocatalysts in the Photocatalytic Production of Hydrogen from Water Revisited

The use of photocatalysts to promote the production of molecular hydrogen from water, following the so-called water splitting reaction, continues to be a promising route for the green production of fuels. The molecular basis of this photocatalysis is the photoexcitation of electrons from the valence band of semiconductors to their conduction band, from which they can be transferred to chemical reactants, protons in the case of water, to promote a reduction reaction. The mechanism by which such a process takes place has been studied extensively using titanium oxide, a simple material that fulfills most requirements for water splitting. However, photocatalysis with TiO 2 tends to be highly inefficient; a cocatalyst, commonly a late transition metal (Au, Pt) in nanoparticle form, needs to be added to facilitate the production of H 2 . The metal is widely believed to help with the scavenging of the excited electrons from the conduction band of the semiconductor in order to prevent their recombination with the accompanying hole formed in the valence band, a step that cancels the initial photon absorption and competes with the photolytic chemical reduction. Here we review and analyze the molecular basis for that mechanism and argue for an alternative explanation, that the role of the metal is to help with the recombination of the atomic hydrogen atoms produced by proton reduction on the semiconductor surface instead. First, we summarize what is known about the electronic structure of these photocatalysts and how the electronic levels need to line up for the reduction of protons in water to be feasible. Next, we review the current understanding of the dynamics of the steps associated with the absorption of photons, the de-excitation via electron–hole pair recombination and fluorescence decay, and the electronic transitions that lead to proton reduction, and contrast those with the rates of the chemical steps required to produce molecular hydrogen. The following section addresses the changes introduced by the addition of the metal cocatalyst, comparatively evaluating its role as either an electron scavenger or a promoter of the recombination of hydrogen atoms. A discussion of the viable chemical mechanisms for the latter pathway is included. Finally, we briefly mention other associated aspects of this photocatalysis, including the possible promotion of H 2 production with visible light via resonant excitation of the surface plasmon of Au nanoparticles, the use of single-metal (Au, Pt) atom catalysts and of yolk–shell nanostructures, and the reduction of organic molecules. We end with a brief personal perspective on the possible generality of the concepts introduced in this Critical Review.

08 HYDROGEN↗

DOE OSTI2023

Virgin-like High-Density Polyethylene from Recycled Mixed Polyolefins

Reported herein is the compatibilization of mixed polyolefins containing a rheology modifier (M-PO RM ) derived from municipal solid waste (MSW) by using different types of compatibilizers. One compatibilizer was produced “in situ” during reactive extrusion (REX), and the other compatibilizers were commercial styrenic block copolymer and maleated polymer-based compatibilizers. Both “in situ” and commercial compatibilizers were first used in laboratory-controlled polyolefins containing a rheology modifier (denoted as L-PO RM ) and were investigated for their mechanical properties. The study was then extended to a rheology modifier containing recycled mixed polyolefins (M-PO RM ), where the effects of both compatibilizers were evaluated. Compared to the in situ and other commercial compatibilizers, the styrenic block copolymer offered superior performance, as it enabled the synthesis of virgin-like high-density polyethylene (HDPE) from the M-PO RM . The findings suggest that M-PO RM can be transformed into blends with virgin HDPE-like properties, thus offering an industrially relevant approach for the re- and upcycling of mixed polyolefins. Finally, the M-PO RM pellets with uniform MFI and good mechanical properties can be used as injection mold feedstocks for different applications such as in the construction and automotive sectors.

compatibilization↗

DOE OSTI2025

Deciphering Catalyst–Support Interaction via Doping for Highly Active and Durable Oxygen Evolution Catalysis

The design of oxygen evolution reaction (OER) electrocatalysts demands a delicate balance between activity and stability. Here, in this study, we present a rational design approach that leverages catalyst-support interactions to enhance both the intrinsic activity and durability of Ir-based catalysts. Our study reveals that while Mo doping energetically promotes the formation of high-valent Ir species, enhancing intrinsic catalytic activity, it also leads to a reduction in electrical conductivity. These findings emphasize that supporting doping can introduce both beneficial and limiting effects, highlighting the need for a carefully balanced design strategy to optimize the overall OER performance. Simultaneously, in situ analytical techniques and comparative evaluation reveal the crucial role of oxide supports in stabilizing the catalyst. These findings highlight the pivotal role of interface engineering in maintaining catalyst integrity and the need for support materials that balance dopant-driven electronic promotion with structural and electrochemical robustness. These interconnected degradation pathways highlight the need to move beyond a catalyst-centric view and instead adopt a system-level understanding of the stability. Our approach offers a strong foundation for the rational design and evaluation of high-performance OER electrocatalysts for electrochemical energy applications.

Kim, Jinyeop [Korea Advanced Inst. Science and Tec↗

DOE OSTI2020

Evaluation method of beam instability in laser ion source using solenoid

In a laser ion source using solenoid field confinement, it is known that an ion beam becomes unstable in the certain range of a magnetic field. Although it is essential to quantify the instability when discussing the unstable region of the beam, it is difficult to evaluate the beam instability by peak current or the amount of charge because an irregular change of temporal profile occurs in addition to the shot-by-shot fluctuation of amplitude. In this study, I propose the most appropriate method to evaluate the beam instability using the difference from an average waveform. The validity of the new method was evaluated by comparing three evaluation methods (variation of maximum value, variation of integral of waveforms, and the proposed evaluation method) with the experimentally obtained waveforms with the stable and unstable regions of a solenoid field. The proposed method was verified to best represent the beam instability by laser-induced plasma.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

Artificial intelligence in cryo-EM protein particle picking: recent advances and remaining challenges

Abstract Cryo-electron microscopy (cryo-EM) has revolutionized structural biology by enabling the determination of high-resolution 3-Dimensional (3D) structures of large biological macromolecules. Protein particle picking, the process of identifying individual protein particles in cryo-EM micrographs for building protein structures, has progressed from manual and template-based methods to sophisticated artificial intelligence (AI)-driven approaches in recent years. This review critically examines the evolution and current state of cryo-EM particle picking methods, with an emphasis on the impact of AI. We conducted a comparative evaluation of popular AI-based particle picking methods, using both general machine learning metrics and specific cryo-EM structure determination metrics. This analysis involved constructing the 3D density map from the picked protein particles and assessing the obtained resolution and particle orientation diversity, underscoring the significant impact of AI on cryo-EM particle picking. Despite the advancements, we also identified key obstacles, such as handling complex micrographs with small proteins. The analysis provides insights into the future development of more sophisticated and fully automated AI methods in cryo-EM particle recognition.

Biochemistry & Molecular Biology↗

DOE OSTI2023

Increasing the bulk of the 1TEL–target linker and retaining the 10×His tag in a 1TEL–CMG2-vWa construct improves crystal order and diffraction limits

TELSAM-fusion crystallization has the potential to become a revolutionary tool for the facile crystallization of proteins. TELSAM fusion can increase the crystallization rate and enable crystallization at low protein concentrations, in some cases with minimal crystal contacts [Nawarathnage et al. (2022), Open Biol. 12 , 210271]. Here, requirements for the linker composition between 1TEL and a fused CMG2 vWa domain were investigated. Ala-Ala, Ala-Val, Thr-Val and Thr-Thr linkers were evaluated, comparing metrics for crystallization propensity and crystal order. The effect on crystallization of removing or retaining the purification tag was then tested. It was discovered that increasing the linker bulk and retaining the 10×His purification tag improved the diffraction resolution, likely by decreasing the number of possible vWa-domain orientations in the crystal. Additionally, it was discovered that some vWa-domain binding modes are correlated with scrambling of the 1TEL polymer orientation in crystals and an effective mitigation strategy for this pathology is presented.

1TEL↗

DOE OSTI2024

PRISTINE: An Emulation Platform for PCB-Level Hardware Trojans

Printed circuit Boards (PCBs) are becoming increasingly vulnerable to malicious design alteration, also known as Trojan attacks, due to a distributed business model that often involves various untrusted parties. Such attacks can be mounted at various stages in the PCB life cycle. The relative ease of alteration of PCB hardware even after fabrication (due to physical access to surface-mounted critical components and traces) makes them attractive for an adversary to manipulate their functional/physical behavior for malicious intent. There is a growing need to explore viable Trojan attacks in a PCB, analyze their functional and physical characteristics (e.g., impact on power or delay), and study the effectiveness of countermeasures against these attacks. While simulation-based approaches for PCB Trojan insertion are effective at creating a large population of possible Trojans, they fail to provide functional feasibility analysis with a realistic workload for a trigger circuit. Also, they cannot estimate a Trojan’s side-channel footprint due to the unavailability of physical models of diverse PCB components. To address these deficiencies, in this paper, we present PRISTINE, a PCB-level emulation system for any integrity or physical tampering issues, specifically, hardware Trojan insertion. The need for building such an emulation platform to resolve PCB trust issues in the supply chain is also surveyed and discussed. Both custom Hardware Hacking (HaHa) boards and multiple commercial PCBs are then used to test the ability of the proposed system to emulate various hardware Trojans specially designed to exploit board-specific hardware characteristics. Experimental results on emulated board-level Trojans show that a wide range of Trojans can be successfully activated, thus enabling the expected payload effects on both types of boards to be studied and quantified. The resulting data are further analyzed to create PCB-level Trojan benchmarks. In particular, a comparative evaluation of the experimental results is used to propose a risk level metric that quantifies the probability of detection and degree of payload impact of each Trojan on a given commercial PCB.

47 OTHER INSTRUMENTATION↗

DOE OSTI2026

Integration of Multiple Real-time Simulation Platforms with AIO for Scalability

This paper introduces a practical and scalable approach to extend interoperability of Controller Hardware in the Loop (CHIL) validations for large scale microgrids, networked microgrids, and power electronics-based feeders. The work focuses on integrating multiple real-time simulators using Analog Input/Output (AIO) interface techniques in heterogeneous CHIL environment. It explores interfacing methods, highlighting key challenges related to dynamic accuracy and maintaining bidirectional power balance. A comparative evaluation of the Ideal Transformer Method is presented, assessing its effectiveness in multi-CHIL integration scenarios. The feasibility of this setup is demonstrated through a real-time use case involving multiple Typhoon HIL and Opal-RT platforms, showcasing its applicability for distributed system studies.

Khalid, Mohammad [ORNL] (ORCID:0000000179208805)↗

DOE OSTI2026

Dual Context: Leveraging Structured Application Context for Code Generation and Runtime Feature Activation via Chat Interfaces

Integrating artificial intelligence (AI) capabilities into software applications typically involves two common paths. For developers, AI assists in generating and documenting source code and other related software engineering efforts. For users, AI assists them through question-and-answer exchanges via chatbots. Both approaches have their value, but neither effectively leverages the modularity of component-based architectures that modern web application frameworks offer. We implement a proof of concept within a centralized suite of applications used for the Atmospheric Radiation Measurement (ARM) Data Center Operational Tools, where we introduce a third integration path through the ARM Context Engine (ACE). ACE is a context driven system that uses structured contextual specifications to enable Large Language Models (LLMs) to render interactive and feature-rich user interface (UI) components directly within chat responses, alongside or in place of conventional text outputs. These specifications serve two important purposes across what we call code context and UI context. Code context provides AI-assisted development tools with structured application knowledge beyond raw code, including component relationships, architectural patterns and schematic information, enabling the generation of consistent, well-structured code. UI context defines the rules for enabling and rendering component features at runtime based on the user's natural language input, allowing end users to activate capabilities such as data export, filtering, and pagination within chat responses, without requiring code changes or redeployment. We demonstrate, through a comparative evaluation against general-purpose AI chatbots, that context-driven component rendering provides interactive capabilities that text-based responses cannot replicate, including deterministic component behavior, application-consistent design language, and on-demand feature activation. A development effort comparison further shows that features that traditionally require multi-step development cycles can be activated with a single naturallanguage request. In this ongoing work, we present ACE as an emerging approach to AI integration that positions modular, well-documented software architecture as the foundation for AI-ready applications. ACE treats context as a shared resource across both development and user-facing AI, bringing cohesion to conventionally disconnected efforts, bridging developer tooling and end-user capabilities within a single framework.

Tadimeti, Vijay [ORNL]↗

DOE OSTI2021

A Modular and Transferable Reinforcement Learning Framework for the Fleet Rebalancing Problem

Mobility on demand (MoD) systems show great promise in realizing flexible and efficient urban transportation. However, significant technical challenges arise from operational decision making associated with MoD vehicle dispatch and fleet rebalancing. For this reason, operators tend to employ simplified algorithms that have been demonstrated to work well in a particular setting. To help bridge the gap between novel and existing methods, we propose a modular framework for fleet rebalancing based on model-free reinforcement learning (RL) that can leverage an existing dispatch method to minimize system cost. In particular, by treating dispatch as part of the environment dynamics, a centralized agent can learn to intermittently direct the dispatcher to reposition free vehicles and mitigate against fleet imbalance. We formulate RL state and action spaces as distributions over a grid partitioning of the operating area, making the framework scalable and avoiding the complexities associated with multiagent RL. Numerical experiments, using real-world trip and network data, demonstrate that RL reduces waiting time by 28% to 38% for the same-day evaluation, 17% to 44% for cross-day evaluation, and 22% to 25% for cross-season evaluation compared with no rebalancing scenarios. This approach has several distinct advantages over baseline methods including: improved system cost; high degree of adaptability to the selected dispatch method; and the ability to perform scale-invariant transfer learning between problem instances with similar vehicle and request distributions.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2025

Concept Lens: Visual Comparison and Evaluation of Generative Model Manipulations

Generative models are becoming a transformative technology for the creation and editing of images. However, it remains challenging to harness these models for precise image manipulation. These challenges often manifest as inconsistency in the editing process, where both the type and amount of semantic change, depend on the image being manipulated. Moreover, there exist many methods for computing image manipulations, whose development is hindered by the matter of inconsistency. This paper aims to address these challenges by improving how we evaluate, compare, and explore the space of manipulations offered by a generative model. We present Concept Lens, a visual interface that is designed to aid users in understanding semantic concepts carried in image manipulations, and how these manipulations vary over generated images. Given the large space of possible images produced by a generative model, Concept Lens is designed to support the exploration of both generated images, and their manipulations, at multiple levels of detail. To this end, the layout of Concept Lens is informed by two hierarchies: a hierarchical organization of (1) original images, grouped by their similarities, and (2) image manipulations, where manipulations that induce similar changes are grouped together. This layout allows one to discover the types of images that consistently respond to a group of manipulations, and vice versa, manipulations that consistently respond to a group of codes. We show the benefits of this design across multiple use cases, specifically, studying the quality of manipulations for a single method, and offering a means of comparing different methods.

clustering↗

DOE OSTI2025

Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker–Planck Equations

The Fokker-Planck (FP) equation is a foundational partial differential equation (PDE) in stochastic processes involving Brownian motions. However, the curse of dimensionality (CoD) poses a formidable challenge when dealing with high-dimensional FP equations. Although Monte Carlo simulation and (vanilla) Physics-Informed Neural Networks (PINNs) have shown the potential to tackle CoD, both methods exhibit significant numerical errors in high dimensions when dealing with the probability density function (PDF) associated with Brownian motion. The point-wise PDF values tend to decrease exponentially as dimensionality increases, surpassing the precision of numerical simulations and resulting in substantial errors. In addition, due to its massive sampling, Monte Carlo fails to offer fast sampling. Modeling the logarithm likelihood (LL) via vanilla PINNs transforms the FP equation into a notoriously difficult Hamilton-Jacobi-Bellman (HJB) equation, which is impractical for PINN learning, whose error grows rapidly with dimension. To this end, we propose a novel approach utilizing a score-based solver to fit the score function in stochastic differential equations (SDEs). The score function, defined as the gradient of the LL, plays a fundamental role in inferring LL and PDF and enables fast SDE sampling, offering an effective means to overcome the CoD. Three fitting methods, Score Matching (SM), Sliced Score Matching (SSM), and Score-PINN, are introduced, each contributing unique advantages in computational complexity, accuracy, and generality. The proposed score-based SDE solver operates in two stages: first, employing score matching or Score-PINN to acquire the score function; and second, solving the LL via an ordinary differential equation (ODE) using the obtained score function. Comparative evaluations across these methods showcase varying trade-offs. The proposed methodology is evaluated across diverse SDEs, including anisotropic Ornstein-Uhlenbeck processes, geometric Brownian motion, and Brownian motion with varying eigenspace. We also test various distributions, including Gaussian, Log-normal, Laplace, and Cauchy distributions. The numerical results demonstrate the score-based SDE solver’s stability, speed, and performance across different experimental settings, solidifying its potential as a solution to CoD for high-dimensional FP equations.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

A computational study of Al n - and Al n -1 1Pt - clusters: the effects of doping and a uniform tuning gauge for single-atom nanocatalysts

Results of density functional theory calculations on Al n - and Al n -1 1Pt - , n = 2-8, clusters are presented and analyzed. The analysis includes different structural forms of the clusters characterized in terms of binding energy, spin and symmetry, and a comparative evaluation of various properties of the two systems viewed as connected through a single-Pt substitutional doping and examined in terms of their respective most stable structures. Furthermore, the Al n -1 1Pt - clusters are then used as a paradigmatic (model) case of single-atom nanocatalysts, with Pt as the catalytic center and Al n-1 as its support, to implement a uniform descriptor for gauging the tuning effects of all the parameters ( "knobs ") of a nanocatalyst that include the identity of the active center and the material and size of its support.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Time-Based CAN IDS Paper Results Code

Modern vehicles are complex cyber-physical systems made of hundreds of electronic control units (ECUs) that communicate over controller area networks (CANs). This inherited complexity has expanded the CAN attack surface which is vulnerable to message injection attacks. These injections change the overall timing characteristics of messages on the bus, and thus, to detect these malicious messages, time-based intrusion detection systems (IDSs) have been proposed. However, time-based IDSs are usually trained and tested on low-fidelity datasets with unrealistic, labeled attacks. This makes difficult the task of evaluating, comparing, and validating IDSs. Here we detail and benchmark four time-based IDSs against the newly published ROAD dataset, the first open CAN IDS dataset with real (non-simulated) stealthy attacks with physically verified effects. We found that methods that perform hypothesis testing by explicitly estimating message timing distributions have lower performance than methods that seek anomalies in a distribution related statistic. In particular, these “distribution-agnostic” based methods outperform “distribution-based” methods by at least 55% in area under the precision-recall curve (AUC-PR). Our results expand the body of knowledge of CAN time-based IDSs by providing details of these methods and reporting their results when tested on datasets with real advanced attacks. Finally, we develop an after-market plug-in detector using lightweight hardware, which can be used to deploy the best performing IDS method on nearly any vehicle.

Moriano, Pablo [Oak Ridge National Lab. (ORNL), Oa↗