Data-driven Modeling and Anomaly Detection of Attacked HATS

The rapid advancements in automated vehicle technology have opened a new era of transportation, promising greater efficiency, safety, and convenience. However, this technological revolution has also introduced new challenges, particularly in the realm of cybersecurity. Highly Automated Vehicles (HAVs) rely on a complex network of sensors and actuators to navigate the environment and perform driving tasks. This system complexity, coupled with the increasing sophistication of cyberattacks, poses a significant threat to the safety and security of Highly Automated Transportation Systems (HATS). This project addresses the challenges of ensuring the safety and security of HATS in the face of cyberattacks, with a focus on stealthy cyberattacks that can bypass traditional detection methods. The project's main components are: (1) Detection and Identification: Detecting and identifying cyberattacks in HAVs is pivotal to maintaining situational awareness, ensuring safe and secure operations, and preventing catastrophic failures. This project develops data-driven techniques to promptly detect cyber threats, anomalous input data and identify the specific components of the HAV system that have been compromised, particularly stealthy cyberattacks that can clandestinely manipulate a small number of sensors while causing potentially severe consequences. (2) Novel Verification and Validation Approaches: Traditional testing and validation methods fall short when dealing with large-scale heterogeneous systems that are vulnerable to sophisticated cyberattacks. This project develops innovative data-driven verification and validation methodologies specifically tailored to the unique characteristics of complex HAV systems. These novel approaches enhance the accuracy and efficiency of safety assessments, providing a more robust defense against cyber vulnerabilities. (3) Testing, Verification, and Validation: Determining the reachable state of HAVs under attack is a formidable challenge, especially given the multitude of potential attack scenarios involving various combinations of sensors. Traditional testing approaches, which often rely on exhaustive testing of all possible scenarios, are resource-intensive and time-consuming, making them unsuitable for dynamic cyber threat landscapes. This project introduces data-driven verification and validation techniques to efficiently assess the safety properties of HAVs when subjected to cyberattacks. These approaches enable the evaluation of HAV system responses under different attack conditions, including single-sensor compromises and combinations of sensor manipulations. By leveraging data-driven methods, the project seeks to ion process, making it more adaptable, accurate, and cost-effective, ultimately contributing to the enhanced safety and security of HAVs.

• Record URL:
  https://utc.engineering.osu.edu/data-driven-modeling-and-anomaly-detection-attacked-hats

Language

• English

Project

• Status: Active
• Funding: $225000
• Contract Numbers:

  69A3552348327

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Center for Automated Vehicle Research with Multimodal Assured Navigation

  Ohio State University
  Columbus, OH  United States  43210
• Project Managers:

  Kline, Robin

• Performing Organizations:

  North Carolina A&T State University

  1601 E. Market Street
  Greensboro, NC  United States  27411
• Principal Investigators:

  Homifar, Abdollah

• Start Date: 20231030
• Expected Completion Date: 20240830
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Computer security; Data analysis; Risk management; Validation
• Subject Areas: Data and Information Technology; Highways; Security and Emergencies; Vehicles and Equipment;

Filing Info

• Accession Number: 01901373
• Record Type: Research project
• Source Agency: Center for Automated Vehicle Research with Multimodal Assured Navigation
• Contract Numbers: 69A3552348327
• Files: UTC, RIP
• Created Date: Dec 4 2023 4:58PM