The Science of Fuzz Testing Autonomous Cyber-Physcial Systems
Abstract
Autonomy holds the potential to transform military and civil life. It is a potential force multiplier, playing a key role in the Air Force’s 2030 Science and Technology Strategy. As systems become increasingly autonomous, the role of human oversight will decrease. Due to this, the consequences of any mistakes in the autonomy, either in design or implementation, are amplified compared with a non-autonomous system. In the military context, these consequences range from mission failure to loss of life. The biggest challenge with autonomy is verification—ensuring the systems work as intended. We propose to research powerful system verification methods by extending the established technique of fuzz testing from pure software systems to cyber-physical systems, where computer systems interact with the physical world.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 21, 2022
- Source ID
- FA95502110121XX0
Entities
People
- Stanley Bak
Organizations
- Air Force Office of Scientific Research
- Research Foundation for the State University of New York
- United States Air Force