Uncovering Failures in Cyber-Physical System State Transitions: A Fuzzing-Based Approach Applied to sUAS

2026-01-09

arXiv.org

AI Summary

This work addresses the challenge of ensuring behavioral reliability in small unmanned aircraft systems (sUAS) during state transitions, autonomous safeguard operations, and human–machine interactions under complex environmental and temporal conditions. To this end, the authors propose SaFUZZ, a novel framework that integrates state-aware fuzz testing with dynamic fault tree generation. SaFUZZ constructs fuzzy specifications to detect behavioral deviations and automatically generates fault trees to uncover the combinations of states, operational modes, and environmental factors leading to system failures. As the first approach to combine state-aware fuzzing with dynamic fault tree analysis, SaFUZZ systematically exposes previously undetected state transition faults in high-fidelity simulations and demonstrates its effectiveness and scalability through real-world hardware validation.

Technology Category

• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Uncertainty Representations
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

The increasing deployment of small Uncrewed Aerial Systems (sUAS) in diverse and often safety-critical environments demands rigorous validation of onboard decision logic under various conditions. In this paper, we present SaFUZZ, a state-aware fuzzing pipeline that validates core behavior associated with state transitions, automated failsafes, and human operator interactions in sUAS applications operating under various timing conditions and environmental disturbances. We create fuzzing specifications to detect behavioral deviations, and then dynamically generate associated Fault Trees to visualize states, modes, and environmental factors that contribute to the failure, thereby helping project stakeholders to analyze the failure and identify its root causes. We validated SaFUZZ against a real-world sUAS system and were able to identify several points of failure not previously detected by the system's development team. The fuzzing was conducted in a high-fidelity simulation environment, and outcomes were validated on physical sUAS in a real-world field testing setting. The findings from the study demonstrated SaFUZZ's ability to provide a practical and scalable approach to uncovering diverse state transition failures in a real-world sUAS application.

Problem

• Cyber-Physical Systems
• sUAS
• State Transitions
• Failsafes
• Behavioral Validation

Innovation

• state-aware fuzzing
• cyber-physical systems
• sUAS
• fault tree generation
• state transition validation