Cybersecurity Assurance via AI-Driven Digital Twins for Transportation Safety

Transportation infrastructure increasingly depends on networked sensor systems for structural health monitoring, yet many operational deployments lack robust data-integrity protections, rendering them vulnerable to cyber-physical attacks. Manipulated sensor readings can misrepresent bridge health, rail conditions, or load limits, thereby creating risks of undetected structural failure, service closures, or catastrophic crashes. Because cyber manipulation directly produces false-safe readings, delays critical maintenance actions, and conceals structural distress, cybersecurity protection constitutes a core safety requirement, not an ancillary concern, for modern monitoring infrastructure. This project develops a secure, artificial intelligence (AI)-driven digital twin framework that continuously compares real-time sensor data against expected behavioral responses to detect spoofing, tampering, replay, and delay manipulation, and other cyber-physical disruptions. The digital twin is intentionally implemented as a lightweight behavioral model; its purpose is not full structural simulation but rather the generation of expected-response profiles that serve as the ground-truth reference for anomaly detection. Combined with secure sensing hardware, AI-based detection algorithms, and survivability logic, the integrated system maintains reliable monitoring capability even under partial cyber compromise. The framework supports the U.S. Department of Transportation (USDOT) Safe System Approach by preventing cyber-induced safety failures and provides a clear pathway to pilot deployment through a Python-based prototype, agency demonstrations, and structured partner engagement. Key milestones include the twin baseline model, secure sensing validation, AI detection module completion , and a survivability demonstration with partner input. The resulting system provides transportation agencies with a low-cost cybersecurity layer that protects safety-critical sensing systems from data manipulation and disruption. Deliverables include a Python detection module, interactive dashboard, and validated datasets compatible with existing DOT workflows. By ensuring the trustworthiness of monitoring data, the proposed approach reduces hazard risk, strengthens maintenance decision-making, and scales across bridges, tunnels, and rail systems, offering a realistic and immediate path to pilot adoption within USDOT transportation-cybersecurity priorities.

Language

• English

Project

• Status: Active
• Funding: $96,000.00
• Contract Numbers:

  69A3552348323

• 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:

  Howard University

  2400 6th Street, NW
  Washington, DC  United States  20059
• Project Managers:

  Bruner, Britain

• Performing Organizations:

  Howard University

  2400 6th Street, NW
  Washington, DC  United States  20059
• Principal Investigators:

  Marin, Claudia

• Start Date: 20260202
• Expected Completion Date: 20260930
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program
• Subprogram: Cybersecurity

Subject/Index Terms

• TRT Terms: Artificial intelligence; Computer security; Data quality; Digital twins; Sensors; Structural health monitoring
• Subject Areas: Bridges and other structures; Data and Information Technology; Maintenance and Preservation; Security and Emergencies; Transportation (General);

Filing Info

• Accession Number: 01978542
• Record Type: Research project
• Source Agency: Research and Education for Promoting Safety (REPS) University Transportation Center
• Contract Numbers: 69A3552348323
• Files: UTC, RIP
• Created Date: Feb 3 2026 3:23PM