Robotic vehicles (also known as drones) are facing various threats of cyber-physical attacks that exploit their security vulnerabilities. RetroV develops automated analysis tools to find such vulnerabilities in existing robotic vehicle systems and retrofit their design against advanced cyber-physical attacks.

Recent News

• Sep. 7, 2022: SensorFuzz poster is accepted to CCS 2022
• Aug. 13, 2020: MAYDAY conference talk at USENIX Security 2020
• May 15, 2020: MAYDAY paper is accepted to USENIX Security 2020

Available Work

• SensorFuzz: A fuzzing tool to test the resilience of robotic vehicles against sensor spoofing attacks (poster)
• MAYDAY: A post-mortem analysis framework for robotic aerial vehicle accidents (paper)
• RVFuzzer: A fuzzing tool to find control-semantic bugs in robotic vehicles (paper)
• Minion: A framework for enforcing memory isolation on real-time microcontrollers (paper)

Acknowledgments

This project is supported in part by the University of Texas at Dallas Office of Research through the NFRS and SPIRe programs, and the Agency for Defense Development.