ACM Journal on Autonomous Transportation Systems最新文献

{"title":"Introduction to Special Issue on Cybersecurity and Resiliency for Transportation Cyber-Physical Systems","authors":"Mizanur Rahman, Mhafuzul Islam, Lipika Deka, Mashrur Chowdhury","doi":"10.1145/3676850","DOIUrl":"https://doi.org/10.1145/3676850","url":null,"abstract":"","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"32 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141924511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Introduction to the Special Issue on Full-Stack Codesign for Robust and Secure AI-Enabled Autonomous Transportation Systems","authors":"Kshitij Bhardwaj, B. Kailkhura, Kartikeya Bhardwaj, Carlee Joe-Wong","doi":"10.1145/3665989","DOIUrl":"https://doi.org/10.1145/3665989","url":null,"abstract":"","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"34 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141814311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Small object intelligent Detection method based on Adaptive Cascading Context","authors":"Jie zhang, Dailin Li, Hongyan Zhang, Fengxian Wang, Yiben Chen, Linwei Li","doi":"10.1145/3665649","DOIUrl":"https://doi.org/10.1145/3665649","url":null,"abstract":"With the technology advances, deep learning-based object detection has made unprecedented progress. However, the small spatial ratio of object pixels affects the effective extraction of deep details features, resulting in poor detection results in small object detection. To improve the accuracy of small object detection, an adaptive Cascading Context small (ACC) object detection method is proposed based on YOLOv5. Firstly, a separate shallow layer feature was proposed to obtain more detailed information beneficial to small object detection. Secondly, an adaptive cascade method is proposed to fuse the output features of the three layers of the pyramid to adaptively filter negative semantic information, while fusing with shallow features to solve the problem of low classification accuracy caused by insufficient semantic information of shallow features. Finally, an adaptive context model is proposed to use a deformable convolution to obtain spatial context features of shallow small objects, associating the targets with the background, thereby improving the accuracy of small object detection. The experimental results show that the detection accuracy of the proposed method has been improved by 6.12%, 3.35%, 3.33%, and 5.2%, respectively, compared with the source code on the PASCAL VOC, NWPU VHR-10, KITTI, and RSOD datasets, which fully demonstrate the effectiveness of our method in small object detection.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141106412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FKeras: A Sensitivity Analysis Tool for Edge Neural Networks","authors":"Olivia Weng, Andres Meza, Quinlan Bock, B. Hawks, Javier Campos, Nhan Tran, J. Duarte, Ryan Kastner","doi":"10.1145/3665334","DOIUrl":"https://doi.org/10.1145/3665334","url":null,"abstract":"\u0000 Edge computation often requires robustness to faults, e.g., to reduce the effects of transient errors and to function correctly in high radiation environments. In these cases, the edge device must be designed with fault tolerance as a primary objective.\u0000 FKeras\u0000 is a tool that helps design fault-tolerant edge neural networks that run entirely on chip to meet strict latency and resource requirements.\u0000 FKeras\u0000 provides metrics that give a bit-level ranking of neural network weights with respect to their sensitivity to faults.\u0000 FKeras\u0000 includes these sensitivity metrics to guide efficient fault injection campaigns to help evaluate the robustness of a neural network architecture. We show how to use\u0000 FKeras\u0000 in the co-design of edge NNs trained on the high-granularity endcap calorimeter dataset, which represents high energy physics data, as well as the CIFAR-10 dataset. We use\u0000 FKeras\u0000 to analyze a NN’s fault tolerance to consider alongside its accuracy, performance, and resource consumption. The results show that the different NN architectures have vastly differing resilience to faults.\u0000 FKeras\u0000 can also determine how to protect neural network weights best, e.g., by selectively using triple modular redundancy on only the most sensitive weights, which reduces area without affecting accuracy.\u0000","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"114 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141125736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Dynamic Threat Prevention Framework for Autonomous Vehicle Networks based on Ruin-theoretic Security Risk Assessment","authors":"Anika Anwar, Talal Halabi, Mohammad Zulkernine","doi":"10.1145/3660527","DOIUrl":"https://doi.org/10.1145/3660527","url":null,"abstract":"In recent years, Autonomous Vehicle Networks (AVNs) have gained significant attention for their potential to make transportation safer and more efficient. These networks rely on Vehicle-to-Vehicle (V2V) communication to exchange critical information, such as location, speed, and driving intentions. However, V2V communication also introduces security vulnerabilities that can be exploited to compromise the safety and privacy of drivers and passengers. Malicious or selfish drivers can potentially intercept, modify, and manipulate V2V communication, causing confusion among vehicles or stealing sensitive data. Therefore, in order to identify and mitigate security threats that could jeopardize V2V communication in AVNs, the implementation of a threat prevention framework is imperative. This paper presents a threat prevention framework that assesses security risks dynamically to facilitate secure message forwarding in V2V communication. First, we propose a dynamic risk assessment technique that utilizes the PIER approach to evaluate the level of security threats posed to V2V communication, and ultimately generate a risk score. Second, we develop a security decay assessment method that utilizes ruin theory to continuously monitor security risk within the AVNs. Third, we design a risk-aware message forwarding protocol based on coalitional game theory to facilitate secure V2V communication. Our experiments using the simulator Veins demonstrate the efficiency and scalability of the proposed framework in preventing potential damage caused by common security threats and enhancing the security of the Automated Highway System (AHS).","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140671787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CANdid\u0000 : A Stealthy Stepping-Stone Attack to Bypass Authentication on ECUs","authors":"Sekar Kulandaivel, Shalabh Jain, Jorge Guajardo, Vyas Sekar","doi":"10.1145/3657645","DOIUrl":"https://doi.org/10.1145/3657645","url":null,"abstract":"A high-entropy source of randomness is an essential component in any secure protocol, required to ensure that protocol elements, such as cryptographic keys, nonces, or salts, are unpredictable for the attackers. Resource-constrained embedded devices, such as Electronic Control Units (ECUs) in modern vehicles, often utilize weak sources of randomness due to the unavailability of true sources of randomness. In this paper, we illustrate the ability of a relatively simple adversary to exploit this weakness within ECUs of vehicles produced by major manufacturers. We demonstrate that the weakness can be exploited by the adversary on a real ECU to breach the protection of Unified Diagnostic Services (UDS) Security Access service and access restricted functionality of the UDS protocol. We develop CANdid, a stepping-stone attack strategy where an adversary with access to a non-critical ECU can utilize this weakness to maliciously reprogram an arbitrary critical ECU over the CAN bus.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":" 35","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140690847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Secure Aggregation for Privacy-preserving Federated Learning in Vehicular Networks","authors":"S. Byun, Arijet Sarker, Sang-Yoon Chang, Jugal Kalita","doi":"10.1145/3657644","DOIUrl":"https://doi.org/10.1145/3657644","url":null,"abstract":"The automotive industry has been enhancing autonomous driving systems utilizing the computation and communication networks embedded in vehicles (e.g., cellular networks and sensors) and roadside units (e.g., radar and cameras). Robust security and privacy requirements are essential in Intelligent Transportation Systems (ITS). To satisfy these requirements, most developed autonomous driving systems (e.g., Waymo and Tesla) use machine learning. Machine learning models trained on sensitive raw data promise improvements in performance; however, they cannot provide privacy for sensitive raw data and users. Federated learning advances privacy-preserving distributed machine learning by aggregating the model parameter updates from individual devices in a secure manner. Security Credential Management System (SCMS) for Vehicle to Everything (V2X) communication provides a guarantee for authentication in a privacy-preserving manner and punishes misbehaving vehicles through misbehavior reporting. In this paper, we design a secure aggregation protocol for privacy-preserving federated learning for vehicular networks. Our protocol allows a server to verify vehicles in a secure manner and is used to aggregate each vehicle-provided global model update for federated learning. We prove our protocol for security in the honest-but-curious framework and detect active adversary attacks, as well as show that it provides trust in different domains (e.g., SCMS and outside the domain of SCMS) and in a privacy-preserving manner for vehicles using SCMS. We analyze the process of federated learning in each vehicle and server while communicating during driving on several types of roads (e.g., local, urban, and rural) using cellular networks (LTE and 5G).","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"20 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140707580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Introduction to the Special Issue Mobility","authors":"Zheng Dong, Weisong Shi, Satish Ukkusuri","doi":"10.1145/3640315","DOIUrl":"https://doi.org/10.1145/3640315","url":null,"abstract":"","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"51 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140730058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ACM Journal on Autonomous Transportation Systems\u0000 : Inaugural Issue Editorial","authors":"Vaneet Aggarwal, Satish Ukkusuri","doi":"10.1145/3652103","DOIUrl":"https://doi.org/10.1145/3652103","url":null,"abstract":"","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"72 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140229728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UAV-Based Delivery Systems: a Systematic Review, Current Trends, and Research Challenges","authors":"Francesco Betti Sorbelli","doi":"10.1145/3649224","DOIUrl":"https://doi.org/10.1145/3649224","url":null,"abstract":"The rising popularity of drones significantly impacts package delivery services, offering both unique opportunities and challenges. This survey explores the diverse applications of drones for last-mile deliveries, highlighting their capacity to access remote areas and create new business prospects. Use cases, ranging from critical medical deliveries to addressing COVID-19 pandemic needs, underscore the transformative potential of drone technology. While recognizing drones’ eco-friendly attributes in eliminating harmful gas emissions, the survey addresses battery constraints, necessitating an investigation into physical energy models to extend flight autonomy. This becomes crucial for operational capabilities, especially in adverse weather conditions. A reliable communication infrastructure is crucial for the success of drone operations in package delivery, especially during unexpected events, as seamless connectivity plays a key role in facilitating efficient control and monitoring between ground stations and drones. This enables dynamic rerouting, enhancing overall delivery reliability. The survey explores innovative approaches, including collaborations with other vehicles like trucks, trains, and buses, optimizing the last-mile delivery process. Despite the transformative potential, concerns about privacy, security, safety, and risk management in drone delivery are acknowledged. The work also emphasizes responsible and ethical implementation, considering diverse concerns associated with widespread adoption.\u0000 In contrast to existing survey articles focused on specific technical aspects, this comprehensive survey broadens its scope. It covers ethical issues, sustainability aspects, healthcare systems, physics models, innovative approaches, reliable communications, security and safety concerns, and real test-beds in drone-based delivery systems. The survey not only identifies potential applications and tackles technical challenges but also integrates broader considerations. In addition, this work extensively explores the motivations, lessons learned, and future directions in the realm of drone delivery. Analyzing existing literature, it provides valuable insights for researchers, industry professionals, policymakers, and stakeholders keen on understanding the dynamic evolution of drone technology in the package delivery domain.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"132 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140443881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}