<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.trb.org/Record/RSS?s=PHNlYXJjaD48cGFyYW1zPjxwYXJhbSBuYW1lPSJzdWJqZWN0bG9naWMiIHZhbHVlPSJvciIgLz48cGFyYW0gbmFtZT0idGVybXNsb2dpYyIgdmFsdWU9Im9yIiAvPjxwYXJhbSBuYW1lPSJsb2NhdGlvbiIgdmFsdWU9IjAiIC8+PC9wYXJhbXM+PGZpbHRlcnM+PGZpbHRlciBmaWVsZD0ia2V5d29yZHMiIHZhbHVlPSImcXVvdDtSb2FkJnF1b3Q7IGFuZCAmcXVvdDtTYWZldHksJnF1b3Q7IGFuZCAmcXVvdDtUZWNobm9sb2d5JnF1b3Q7IGFuZCAmcXVvdDtQcml2YWN5JnF1b3Q7IiBvcmlnaW5hbF92YWx1ZT0iUm9hZCBTYWZldHksIFRlY2hub2xvZ3kgYW5kIFByaXZhY3kiIC8+PC9maWx0ZXJzPjxyYW5nZXMgLz48c29ydHM+PHNvcnQgZmllbGQ9InB1Ymxpc2hlZCIgb3JkZXI9ImRlc2MiIC8+PC9zb3J0cz48cGVyc2lzdHM+PHBlcnNpc3QgbmFtZT0icmFuZ2V0eXBlIiB2YWx1ZT0icHVibGlzaGVkZGF0ZSIgLz48L3BlcnNpc3RzPjwvc2VhcmNoPg==" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>Shaping the future of cycling safety: A research agenda for the next two decades</title>
      <link>https://trid.trb.org/View/2669927</link>
      <description><![CDATA[The global shift toward sustainable transportation has raised the profile of cycling. Yet cycling safety still faces persistent challenges (e.g., fragmented governance, inequitable infrastructure, scarce research) that are often overshadowed by motorized transport agendas. This paper presents findings from a workshop held at the 12th International Cycling Safety Conference (ICSC2024) in Imabari, Japan, which brought together an interdisciplinary group of 31 experts (researchers, practitioners, and policymakers) to explore prospective research directions for cycling safety over the next two decades. Drawing on submitted abstracts, group dialogues, and post-event reflections, we used participatory methods, speculative exercises, and collaborative discussions to conduct a thematic analysis that organized key factors into five domains: society, policy, infrastructure, vehicles, and road users. This framework supports a long-term research agenda to address the interconnected challenges of cycling safety. Key priorities include: (i) behavioral and societal studies to make cycling safer and more appealing for diverse users; (ii) development of AI-enabled safety technologies; (iii) establishment of international infrastructure standards; and (iv) tools to anticipate risks linked to emerging vehicle technologies. Additional directions involve the use of eXtended Reality (XR) for behavioral research, multimodal integration, and the ethical and privacy dimensions of data collection. Practically, the findings highlight the importance of participatory and multidisciplinary approaches for tackling real-world safety issues and guiding future research.]]></description>
      <pubDate>Tue, 12 May 2026 09:11:57 GMT</pubDate>
      <guid>https://trid.trb.org/View/2669927</guid>
    </item>
    <item>
      <title>TraCR Foundational Project: TraCR Collective Transportation Cybersecurity Testbeds</title>
      <link>https://trid.trb.org/View/2697454</link>
      <description><![CDATA[The National Center for Transportation Cybersecurity and Resiliency's (TraCR's)
foundational project aims to develop technological tools, prototypes, testing platforms, and facilities to ensure the cybersecurity and cyber-resilience of multimodal transportation systems and related infrastructure. The project is led by Clemson University (Clemson) under the strategic direction of Dr. Ronnie Chowdhury (Lead PI), with coordination support from Dr. Sabbir Salek (Co-PI), and involves all eight other TraCR partner institutions organized into four subgroups. A structured project governance framework, including biweekly subgroup meetings, monthly full-team coordination meetings, quarterly progress reporting and advisory board engagement, ensures alignment with project milestones, integration across teams, and effective monitoring of technical progress and deliverables. 

Clemson collaborates with Benedict College (Benedict), South Carolina State University (SCSU), and the University of Texas at Dallas (UTD) to advance a comprehensive, automated threat modeling capability for multimodal transportation systems. Building on the Transportation Cybersecurity and Resiliency Threat Modeling Framework (TraCR-TMF), the team conducts testbed-in-the-loop evaluations within Clemson’s real-world cybersecurity testbed, implementing digital-twin-based cybersecurity analysis of in-vehicle networks, and engaging state transportation agencies to assess operational transferability. Additionally, the team will work to integrate graph-based reasoning models into threat modeling, deploy supervised ModernBERT classifiers, and align with the MITRE Embedded Systems Threat Matrix to strengthen structured system-to-vulnerability mapping and improve threat coverage across transportation cyber-physical systems.

The other partner institutions will develop additional real-world and virtual testing platforms to support cybersecurity experimentation for multimodal transportation. Florida International University (FIU) and the University of Alabama at Tuscaloosa (UA) are jointly advancing the Open-Source Connected and Automated Mobility Co-Simulation (OpenCAMS) environment and related simulation platforms, integrating SUMO, CARLA, and network simulation tools, to evaluate privacy-aware multimodal large language models and post-quantum-secure C-V2X communications. Their efforts further include the development and validation of spoofing attack models targeting Basic Safety Message transmissions and multi-frequency GPS receivers, as well as investigations into backdoor-resilient perception systems and the security of vision-language models for intelligent transportation applications.

Purdue University (Purdue) and the University of California, Santa Cruz (UCSC) are advancing adversarial testing methodologies through integrated physical-virtual experimentation frameworks that combine miniature autonomous vehicle testbeds, CARLA/METS-R simulation coupling, and scenario-based vulnerability discovery. These activities include simulation-to-real validation of perception and traffic signal spoofing attacks, evaluation of V2X safety message vulnerabilities, cybersecurity analysis of shared micromobility Bluetooth pairing protocols, implementation of lightweight post-quantum cryptographic protections for vulnerable road user beacons, and closed-loop security assessments of traffic signal controller infrastructures, along with investigations of secure multimodal AI agents and memory-augmented reasoning architectures for autonomous robotic transportation systems.

In addition, Morgan State University (MSU) is enhancing its connected vehicle cybersecurity experimentation capabilities by developing replay-attack models targeting C-V2X onboard units and evaluating mitigation strategies in its real-world testbed environment, in collaboration with Clemson. These efforts quantify communication-level impacts on safety-critical applications and support the development of deployable countermeasures to strengthen resilience against wireless attack vectors affecting connected transportation infrastructure.
]]></description>
      <pubDate>Thu, 30 Apr 2026 12:19:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2697454</guid>
    </item>
    <item>
      <title>Data Streaming Platform for Crowd-Sourced Vehicle Dataset Generation</title>
      <link>https://trid.trb.org/View/2659104</link>
      <description><![CDATA[Vehicles are sophisticated machines equipped with sensors that provide real-time data for onboard driving assistance systems. Due to the wide variety of traffic, road, and weather conditions, continuous system enhancements are essential. Connectivity allows vehicles to transmit previously unknown data, expanding datasets and accelerating the development of new data models. This enables faster identification and integration of novel data, improving system reliability and reducing time to market. Data Spaces aim to create a data-driven, interconnected, and innovative data economy, where edge and cloud infrastructures support a virtualised IoT platform that connects data sources and development servers. This paper proposes an edge-cloud data platform to connect car data producers with multiple and heterogeneous services, addressing key challenges in Data Spaces, such as data sovereignty, governance, interoperability, and privacy. The paper also evaluates the data platform's performance limits for text, image, and video data workloads, examines the impact of connectivity technologies, and assesses latencies. The results show that latencies drop to 33 ms with 5G connectivity when pipelining data to consuming applications hosted at the edge, compared to around 77 ms when crossing both edge and cloud processing infrastructures. The results offer guidance on the necessary processing assets to avoid bottlenecks in car data platforms.]]></description>
      <pubDate>Wed, 29 Apr 2026 09:10:08 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659104</guid>
    </item>
    <item>
      <title>Federated Learning for Drowsiness Detection in Connected Vehicles</title>
      <link>https://trid.trb.org/View/2579238</link>
      <description><![CDATA[Ensuring driver readiness poses challenges, yet driver monitoring systems can assist in determining the driver’s state. By observing visual cues, such systems recognize various behaviors and associate them with specific conditions. For instance, yawning or eye blinking can indicate driver drowsiness. Consequently, an abundance of distributed data is generated for driver monitoring. Employing machine learning techniques, such as driver drowsiness detection, presents a potential solution. However, transmitting the data to a central machine for model training is impractical due to the large data size and privacy concerns. Conversely, training on a single vehicle would limit the available data and likely result in inferior performance. To address these issues, we propose a federated learning framework for drowsiness detection within a vehicular network, leveraging the YawDD dataset. Our approach achieves an accuracy of 99.2%, demonstrating its promise and comparability to conventional deep learning techniques. Lastly, we show how our model scales using various number of federated clients.]]></description>
      <pubDate>Tue, 31 Mar 2026 16:34:42 GMT</pubDate>
      <guid>https://trid.trb.org/View/2579238</guid>
    </item>
    <item>
      <title>A Multi-Agent Federated Reinforcement Learning-Based Cooperative Vehicle-Infrastructure Control Approach Framework for Roundabouts</title>
      <link>https://trid.trb.org/View/2610682</link>
      <description><![CDATA[In contrast to autonomous driving (AD) systems based on a single vehicle, the intelligent vehicle infrastructure cooperative system enables intelligent connected vehicles (ICVs) to perform active safety control and road collaboration management through vehicle-Infrastructure dynamic information interaction. However, complex intersections involve a wide range of interactions between agents, traffic participants and road infrastructures. The presence of time-varying traffic conditions and redundant traffic information may impede the efficiency and effectiveness of the vehicle-infrastructure system. Meanwhile, existing cooperative systems typically assume voluntary client access and data sharing, overlooking the information asymmetry challenges stemming from privacy awareness and the model interpretability challenges associated with data-driven approaches. This paper proposes a federated reinforcement learning (FRL) architecture for vehicle-infrastructure cooperative control is predicated on data and rule fusion, with the objective of considering privacy awareness and sample efficiency by employing a screening-based dual aggregation federated learning (FL) method. The proposed architecture enhances the interpretability of the algorithmic framework at four perspectives: modeling, training, optimization, and application. In this paper, we initially undertake training and performance comparisons on the OpenDD real traffic roundabout road driving dataset, and then extend the proposed method to more complex Nocrash benchmarks and real-world campus traffic environment for algorithm scalability validation.]]></description>
      <pubDate>Fri, 27 Mar 2026 17:03:28 GMT</pubDate>
      <guid>https://trid.trb.org/View/2610682</guid>
    </item>
    <item>
      <title>Tracking Vehicles in Cooperative Intelligent Transportation Systems: Attacks, Defense Solutions, and Future Directions</title>
      <link>https://trid.trb.org/View/2617671</link>
      <description><![CDATA[The Cooperative Intelligent Transportation System (C-ITS) is vital in enhancing road safety, improving traffic efficiency, and increasing user comfort for pedestrians and drivers. However, as vehicle communications evolve, security threats that aim to undermine critical security services, such as data confidentiality, integrity, and privacy, have become crucial issues that must be addressed. Privacy, the freedom from interference or intrusion, is also considered one of the most significant challenges in computer networks and connected vehicles. Privacy in C-ITS can be protected by preventing both the collection of personal information and the tracking of vehicles by malicious users. Tracking is often achieved through the periodic transmission of Cooperative Awareness Messages (CAMs), which contain spatio-temporal information such as position and speed. We investigate key tracking-related critical issues in intelligent connected vehicles. We highlight current security challenges and attacks that lead to the unauthorized tracking of connected cars. We discuss various defense solutions proposed in the literature to address these challenges. We classify these solutions into two groups: general (addressing eavesdropping, Sybil, etc.) and pseudonym change (addressing correlation, swap, silent periods, and mix-zones). Finally, we explore robust future strategies to prevent tracking attacks on the C-ITS.]]></description>
      <pubDate>Tue, 24 Mar 2026 17:01:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2617671</guid>
    </item>
    <item>
      <title>Accurate Collection and Reporting of Worker Presence in Work Zones</title>
      <link>https://trid.trb.org/View/2680117</link>
      <description><![CDATA[Highway work zones remain high-risk environments due to the close interaction between workers, live traffic, and heavy equipment. While platforms like the Work Zone Data Exchange (WZDx) and state Department of Transportation (DOT) traveler information maps provide location and traffic impact data, real-time, verified information regarding actual worker presence is often unavailable. This data gap limits the effectiveness of smart work zone deployments and emerging connected vehicle applications. This study evaluated device-based location technologies for highway work zone applications by comparing Global Navigation Satellite System (GNSS) and Bluetooth Low Energy (BLE) approaches. Results indicated that BLE devices relying on crowdsourced networks produced inconsistent reporting and large location errors, particularly in rural areas, while GNSS devices provided more stable and temporally consistent data but involved tradeoffs related to cost, battery life, and data accessibility. To address these limitations, the research developed the WZ-Gateway Node, an open-source prototype that utilizes shared communication to reduce recurring costs. Complementing the hardware, the MU Worker Presence Platform was developed to process device-level data into validated worker presence attributes. By applying spatial buffering and activity classification logic, the platform filters false positives and protects worker privacy while accurately associating field activity with work zone characteristics. Field evaluations confirmed the platform’s ability to generate WZDx-compliant feeds with real-time, verified worker presence information. These findings offer a practical roadmap for Missouri DOT and other transportation agencies to enhance traveler safety, smart work zone operations, and connected vehicle applications by basing worker presence alerts on actual field conditions.]]></description>
      <pubDate>Mon, 23 Mar 2026 08:34:48 GMT</pubDate>
      <guid>https://trid.trb.org/View/2680117</guid>
    </item>
    <item>
      <title>Harnessing AI-driven behavioral analytics for sustainable urban mobility: An interdisciplinary approach to policy, planning, and user adaptation</title>
      <link>https://trid.trb.org/View/2673319</link>
      <description><![CDATA[Transportation in urban settings has undergone a revolution due to advances in technology, as well as the imperative to adopt eco-friendly transportation solutions. In this paper, the authors investigate the effectiveness of adopting artificial intelligence-powered behavioral analysis in promoting an effective transportation revolution in urban settings, combining an interdisciplinary approach that considers transportation research sciences and the perspectives of economic and transportation behavior. The effectiveness of artificial intelligence solutions in transport within the realm of research relates to understanding whether transport decision-making methodologies can create an ecosystem of intelligent transport by introducing artificial intelligence elements. The authors critically analyze whether machine intelligence solutions within artificial intelligence can enhance transport decision-making processes and encourage transport users to adopt eco-friendly transportation. The findings indicate that artificial intelligence solutions can play a crucial role in creating an efficient transportation system by adapting to users’ preferences for more user-friendly transport solutions. At the same time, the limitations of artificial intelligence solutions, stemming from algorithmic challenges and data privacy concerns, underscore the need for an imperative solution that incorporates transport intelligence within an artificial intelligence framework. The paper provides an empirical analysis suggesting that artificial intelligence solutions in an environmental transport system should play a significant role in shaping users toward intelligent transport solutions. The research supports the assumption that artificial intelligence solutions within intelligent transportation systems should prioritize the imperative of artificial intelligence in transportation solutions.]]></description>
      <pubDate>Wed, 18 Mar 2026 09:00:16 GMT</pubDate>
      <guid>https://trid.trb.org/View/2673319</guid>
    </item>
    <item>
      <title>Reputation System-Based Vehicle Violation Reporting Service With Invalid Signature Identification in VANETs</title>
      <link>https://trid.trb.org/View/2591252</link>
      <description><![CDATA[Owing to frequent traffic accidents, the violation reporting service is a promising method to enhance road safety in vehicular ad hoc networks (VANETs). However, to implement such a service, it is critical to ensure security, privacy, and efficiency when vehicles send messages to roadside units (RSU). In this study, to address these issues, a vehicle violation reporting service is proposed using reputation systems and a physically unclonable function. The proposed scheme ensures secure authentication between vehicles and RSUs, facilitates an efficient search for invalid signatures, and overcomes the limitations present in ID-based conditional privacy-preserving authentication schemes. Moreover, considering the dynamic VANET environment, the distribution of invalid signatures may vary across multiple scenarios. Therefore, a fault-tolerant mechanism is proposed to ensure the robustness of this approach. Security proof with the random oracle model and detailed security analysis proved that the scheme could satisfy the security requirements of VANETs. Our scheme outperforms related approaches in terms of authentication overhead and the identification of invalid signatures, achieving superior performance in both aspects.]]></description>
      <pubDate>Wed, 04 Mar 2026 09:17:03 GMT</pubDate>
      <guid>https://trid.trb.org/View/2591252</guid>
    </item>
    <item>
      <title>Industrial Intelligence for Smart Cities: The Role of Ai and Iot in Transforming Urban Mobility and Infrastructure</title>
      <link>https://trid.trb.org/View/2665615</link>
      <description><![CDATA[This review synthesizes research on AI and IoT in urban mobility, focusing on traffic management, public transportation systems, and autonomous vehicles to address escalating urban congestion, environmental impact, and mobility demands. This review aimed to evaluate AI and IoT applications in traffic flow optimization, benchmark integration in public transit, identify autonomous vehicle frameworks, compare predictive models and sensor networks, and analyze adoption challenges. A systematic analysis of global empirical, simulation, and theoretical studies was conducted, emphasizing technological convergence, performance outcomes, data utilization, and barriers. The findings reveal that AI-driven predictive models combined with IoT sensor networks significantly improve traffic efficiency and reduce emissions, whereas AI-IoT integration enhances public transit reliability through predictive maintenance and dynamic scheduling. Autonomous vehicles, supported by IoT-enabled communication and AI decision-making, demonstrate the potential for safety and sustainability gains but face regulatory, infrastructural, and acceptance challenges. Advanced machine learning techniques optimize real-time data analytics but encounter scalability and explainability limitations. Collectively, these findings underscore the transformative potential of AI-IoT in urban mobility, contingent on addressing privacy, infrastructure, and social factors. The synthesis highlights the need for interdisciplinary approaches to advance scalable, secure, and user-centered AI-IoT urban mobility solutions that inform future research and practical implementations.]]></description>
      <pubDate>Thu, 26 Feb 2026 17:01:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/2665615</guid>
    </item>
    <item>
      <title>Leveraging Retrieval-Augmented Generation for Efficient Extraction of Transportation Safety Insights</title>
      <link>https://trid.trb.org/View/2663704</link>
      <description><![CDATA[This study evaluated two approaches for extracting information for use in large language models from transportation safety datasets: retrieval-augmented generation applied to PDF files and an agent-based system applied to structured traffic records. Results show that system accuracy is highly dependent on data preparation. Treating PDFs as plain text limited accuracy to approximately 38 percent, whereas preserving tabular structures or supplementing them with concise summaries raised accuracy above 80 percent. The agent-based system demonstrated strong performance with exact matches in road names and directions but showed reduced reliability when queries diverged from the data’s wording. For transportation professionals, these findings underscore both the current limitations and the emerging potential of large language models and related AI tools. Challenges remain in managing diverse data formats, ensuring consistency, and addressing privacy concerns. However, the study shows that presenting data in a structured format, coupled with contextual guidance, significantly enhances retrieval performance. Moreover, localizing retrieval processes may help further mitigate privacy risks.]]></description>
      <pubDate>Thu, 26 Feb 2026 09:22:45 GMT</pubDate>
      <guid>https://trid.trb.org/View/2663704</guid>
    </item>
    <item>
      <title>A Robust and Efficient Traffic Signal Recognition Framework for Autonomous Bus Real-Time Control</title>
      <link>https://trid.trb.org/View/2613102</link>
      <description><![CDATA[Real-time traffic light detection ensures the safe operation of autonomous vehicles. While external V2X systems can transmit traffic light status on fixed routes to autonomous buses (ABs), limitations such as communication delays and data privacy require alternative solutions. By leveraging internal visual perception, the vehicle’s camera images are analyzed to accurately detect traffic lights, even when they occupy minimal pixels. However, current models often fail to validate the information, and detecting irrelevant signals can impair ABs’ decision-making. To address this, we propose a Robust and Efficient Traffic Signal Recognition Framework for Autonomous Bus Real-Time Control, which utilizes a 3D HD map transformed 2D traffic light plane projection, a lightweight detection model, and an HSV classifier to identify traffic signals from incoming single-frame images. Given that ABs rely on sequential traffic light information for real-time operation, we introduced the Anomalous Flicker Filtering Algorithm (AFFA) to handle flickering, black, or missing lights, ensuring only continuous information is sent to the ABs’ control system. Our proposed architecture not only demonstrates high accuracy in offline tests but also assists safe stopping during real-world trials. Furthermore, we introduce a comprehensive traffic light data set that encompasses a variety of traffic scenes, including congested roads, day, and night.]]></description>
      <pubDate>Fri, 20 Feb 2026 15:28:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2613102</guid>
    </item>
    <item>
      <title>Interplay Between Security, Privacy and Trust in 6G-Enabled Intelligent Transportation Systems</title>
      <link>https://trid.trb.org/View/2658734</link>
      <description><![CDATA[Advancements in sixth-generation (6G) wireless technology are expected to transform the transportation sector by enabling faster, more reliable, and more intelligent mobility services. 6G-enabled Intelligent Transportation Systems (ITS) offer ultra-low-latency communication, massive connectivity, and advanced analytics that support safer, more efficient, and more sustainable mobility. Despite these benefits, 6G-ITS introduces significant security, privacy, and trust challenges that must be addressed to ensure safe deployment and sustained public confidence. This paper reviews the opportunities and challenges of 6G-ITS with a focus on security, privacy, and trust, including the dual role of quantum technologies that strengthen cryptographic mechanisms while introducing novel attack surfaces. The paper highlights the benefits of 6G for transportation, including improved communication performance, enhanced device interoperability, advanced data analytics, and increased automation across transportation management and communication systems. A taxonomy of attack models in 6G-ITS is provided, alongside a comparison of security threats in 5G-ITS and 6G-ITS and corresponding mitigation strategies. The findings highlight the need for a comprehensive, multi-layered security framework that spans physical infrastructure, network protocols, data management, application security, and trust mechanisms to ensure the integrity and resilience of future 6G transportation ecosystems.]]></description>
      <pubDate>Thu, 19 Feb 2026 10:53:39 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658734</guid>
    </item>
    <item>
      <title>Artificial intelligence, machine learning and deep learning in advanced transportation systems, a review</title>
      <link>https://trid.trb.org/View/2618645</link>
      <description><![CDATA[Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) are revolutionizing transportation systems, addressing critical challenges such as congestion, inefficiency, safety, and sustainability. This paper provides a comprehensive review of these transformative technologies, exploring their applications across various domains, including traffic management, autonomous vehicles, smart parking systems, public transit optimization, freight and logistics, sustainability initiatives, safety enhancements, and infrastructure monitoring. Real-world implementations are examined, highlighting their successes and limitations in practical contexts. While AI-driven solutions have demonstrated significant potential, they face persistent challenges, including data scarcity, limited model generalization, and high computational demands that hinder scalability and reliability. Ethical and regulatory issues, including bias, accountability, and privacy concerns, further complicate adoption. This paper identifies these challenges and discusses emerging research opportunities, such as federated learning, multimodal transportation optimization, and energy-efficient AI systems, to address gaps and advance the field. By synthesizing current advancements, identifying limitations, and proposing future directions, this paper emphasizes the critical role of AI, ML, and DL in shaping smarter, safer, and more sustainable transportation systems.]]></description>
      <pubDate>Wed, 11 Feb 2026 09:17:42 GMT</pubDate>
      <guid>https://trid.trb.org/View/2618645</guid>
    </item>
    <item>
      <title>Automotive cybersecurity : from risk assessment to mitigation</title>
      <link>https://trid.trb.org/View/2666563</link>
      <description><![CDATA[As road vehicles are increasingly defined by their software capabilities and connected service infrastructure, it has become widely accepted that cybersecurity is vital to keep road users and their environment safe and secure. Failures of vehicular cybersecurity can lead to loss of life, severe injuries, financial losses and breaches of privacy. Automotive system development faces several challenges, including long development lead times and system life-times, highly heterogeneous hardware, multi-tiered supply chains and legal, safety and real-time requirements. These challenges frame the available design choices. An effective cybersecurity concept must be rooted in a thorough understanding of the risks associated with connected vehicles. Furthermore, efficient processes are essential for responding to newly discovered vulnerabilities and incidents. This thesis aims to deepen our understanding of these issues through three primary objectives: (1. to explore the systematization of threat analysis and risk assessment to facilitate cybersecurity requirements engineering, (2. to examine how cybersecurity engineering processes can be implemented to address cybersecurity issues effectively, and (3. to analyze the influence of automotive technology on the design of cybersecurity measures. The first part of this thesis focuses on risk assessment and standardization by (a) developing a risk assessment methodology which influenced ISO/SAE 21434, an automotive cybersecurity engineering standard, (b) updating the risk assessment methodology to fully align with the standard, and (c) critically analyzing ISO/SAE 21434 to identify conceptual weaknesses, while proposing improvements to its threat analysis and risk assessment framework, and vulnerability and incident handling processes. The second part focuses on the design and implementation of risk mitigation measures by examining (i) common automotive cybersecurity design issues, (ii) memory exploitation and protection techniques for resource-constrained electronic control units, (iii) the impact of the CAN bus's technical constraints on authentication protocols and (iv) the potential of 5G telecommunication technology to strengthen security in vehicle-to-everything communication.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:34:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666563</guid>
    </item>
  </channel>
</rss>