泛研网

公众版 查看说明
全球科研项目数据库2026版

Collaborative Research:SaTC:CORE:Small:NSF-DST:Towards Secure and Resilient Collaborative Autonomous Driving(CoAD)

项目来源

美国国家科学基金(NSF)

项目主持人

Chunming Qiao

项目受资助机构

SUNY at Buffalo

项目编号

2413876

财政年度

2025,2024

立项时间

未公开

项目级别

国家级

研究期限

未知 / 未知

受资助金额

601452.00美元

学科

未公开

学科代码

未公开

基金类别

Standard Grant

关键词

Secure&Trustworthy Cyberspace ; International Partnerships ; SaTC:Secure and Trustworthy Cyberspace ; SMALL PROJECT

参与者

未公开

参与机构

THE RESEARCH FOUNDATION FOR THE STATE UNIVERSITY OF NEW YORK

项目标书摘要：This project aims to investigate both the security and robustness of Collaborative Autonomous Driving(CoAD)to improve the safety and resiliency of connected and autonomous vehicles(CAVs).Despite being an emergent trend,CoAD systems,consisting of collaborative CAVs and Roadside Units(RSUs),are a new type of cyber-physical systems(CPS)that have received little attention in the research community,especially in terms of their security and resiliency.To conduct the proposed research,the proposers will build upon the team’s complementary expertise in a wide range of topics including vehicle security,Vehicle-to-Everything(V2X)security,adversarial attacks to the Artificial Intelligence(AI)-powered perception subsystem,formal methods and verification,robust control,and end-to-end evaluation.The project will take a systematic approach and develop a comprehensive framework when examining new attack vectors/surfaces in the CoAD systems,and propose novel mitigation and defense mechanisms.is an integrated effort by two PIs from the University at Buffalo(UB),and UC Irvine(UCI)from the US side,and two PIs from the Indian Institute of Technologies(IIT)at Kharagpur(IIT-KGP)and Jodphur(IIT-J)from the India side.The project is expected to result in joint publications as a part of dissemination efforts,joint mentoring of students by the US and India PIs,and new datasets,as well as increased public awareness of cyber-security threats and trust in the resilience of autonomous driving.In addition,new course and publicly available materials based on research results will be developed to attract and train students,including under underrepresented minority students.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人员信息

Chunming Qiao(Principal Investigator)：qiao@computer.org；

机构信息

【SUNY at Buffalo(Performance Institution)】StreetAddress：520 LEE ENTRANCE STE 211,AMHERST,New York,United States/ZipCode：142282577；【THE RESEARCH FOUNDATION FOR THE STATE UNIVERSITY OF NEW YORK】StreetAddress：520 LEE ENTRANCE STE 211,AMHERST,New York,United States/PhoneNumber：7166452634/ZipCode：142282577；

项目主管部门

Directorate for Computer and Information Science and Engineering(CSE)-Division Of Computer and Network Systems(CNS)

项目官员

Selcuk Uluagac(Email：suluagac@nsf.gov；Phone：7032924540)

  • 排序方式：
  • 1
  • /

  • 1.Dynamic Defense for Car-Borne LiDAR Vehicle Detection

    • 关键词：
    • Embedded systems;Error detection;Network security;Object detection;Object recognition;Open Data;Vehicle detection;Detection models;Embedded-system;Objects detection;Real objects;Real world experiment;Runtimes;State of the art;Systems implementation;Vehicles detection
    • Xu, Yihan;Guo, Dongfang;Song, Qun;Lou, Yang;Zhu, Yi;Wang, Jianping;Qiao, Chunming;Tan, Rui
    • 《23rd ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2025》
    • 2025年
    • June 23, 2025 - June 27, 2025
    • Anaheim, CA, United states
    • 会议

    Adversarial attacks with real objects or lasers on car-borne LiDAR-based object detection are concerning. The existing defense approaches are often designed to address specific attacks and short of considering adaptive attackers who may adapt based on all available information about the deployed defense to maximize attack effect. This paper proposes Hyper3Def, a new defense for the function of detecting vehicle objects, which uses a Hypernet to generate an ensemble of multiple new detection models when needed at run time. The detection results of these models are fused to give the final result. As a dynamic defense, Hyper3Def revokes an important basis of the adaptive attack, i.e., the object detection model is needed to plan effective adversarial perturbations. Evaluation based on open data and real-world experiments with embedded system implementation show that, when confronting adaptive attacks, Hyper3Def outperforms various baseline defenses including the adversarial training, which is often cited as the state of the art. © 2025 Copyright held by the owner/author(s).

    ...
  • 排序方式：
  • 1
  • /