Assurance and Security for AI CPS
Abstract
Assurance for AI CPS (e.g., Autonomy) Assurance of AI Enable ML to- Detect complex patterns (object recognition), handle uncertainty Interact with unknown environment Cyber-Physical Systems (Most Systems in Field) React to physical environment Safe behavior: safe actions at right time (e.g., prevent crash) Security : ensure attacker does not make system crash
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 25, 2022
- Accession Number
- AD1161237
Entities
People
- Dionisio de Niz
Organizations
- Carnegie Mellon University