Domain Invariant Semantic-Segmentation for Robustness Against Adversarial Attacks on Autonomous Vehicles

The project ‘Domain Invariant Semantic-Segmentation for Robustness Against Adversarial Attacks on Autonomous Vehicles’ aims to develop a robust artificial intelligence (AI) framework for real-time semantic segmentation of scenarios encountered by vision systems in connected autonomous vehicles (CAVs). Overall, the project will make multiple novel contributions throughout the development of the proposed segmentation system. In particular (1): Using different categories of adversarial attacks discussed in the literature coupled with efficient novel attacks, the research team will algorithmically generate a diverse set of attacked training datasets relevant for development of adversarially robust semantic segmentation systems of the future. (2): Using concepts from domain generalization and casual AI literature, the team will use the generated dataset to develop robust semantic segmentation algorithms for real-time inference in CAVs. (3): For keeping the developed approach relevant for attacks of the future, the project also aims to develop a continuous learning analog of the proposed segmentation approach.

• Supplemental Notes:
  • This material is based on work supported by the U.S. Department of Transportation, OST-R, University Transportation Center Program, the USDOT Tier 1 UTC Transportation Cybersecurity Center for Advanced Research and Education (CYBER-CARE).

Language

• English

Project

• Status: Active
• Funding: $52,000.00
• Contract Numbers:

  69A3552348332

• 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:

  Transportation Cybersecurity Center for Advanced Research and Education (CYBER-CARE)

  University of Houston
  Houston, TX  United States 
• Project Managers:

  Zhang, Yunpeng (Jack)

• Performing Organizations:

  Embry-Riddle Aeronautical University

  600 S. Clyde Morris Boulevard
  Daytona Beach, Fl  United States  32114
• Principal Investigators:

  Shekhar, Prashant

• Start Date: 20240701
• Expected Completion Date: 20260630
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Algorithms; Artificial intelligence; Autonomous vehicles; Computer security; Connected vehicles
• Subject Areas: Data and Information Technology; Highways; Security and Emergencies; Vehicles and Equipment;

Filing Info

• Accession Number: 01956891
• Record Type: Research project
• Source Agency: Transportation Cybersecurity Center for Advanced Research and Education (CYBER-CARE)
• Contract Numbers: 69A3552348332
• Files: UTC, RIP, STATEDOT
• Created Date: May 29 2025 9:32PM