Ortiz Barbosa, D. (CSE) – HARDENING AUTONOMOUS CYBER-PHYSICAL SYSTEMS AGAINST ADVERSARIAL CONDITIONS

Autonomous systems, such as Autonomous Vehicles (AVs) and drones, are increasingly
deployed across a wider array of contexts for both civilian and military use. As these
systems become more common, they may be targeted by malicious actors seeking to
exploit and abuse them, compromising safety-critical operations. Among the ways to
protect these systems simulation based testing frameworks have been developed. How-
ever, existing testing frameworks primarily focus on identifying logical flaws or system
vulnerabilities, often emphasizing static scenarios and paying less attention to an adap-
tive intelligent adversary.
To help reduce this gap, this dissertation develops and applies adaptive, adversary-
aware methodologies to discover, formalize, and mitigate security vulnerabilities in au-
tonomous systems spanning vehicle platooning, drone swarms, and vision-based drone
recovery. We first apply NLP techniques to discover and formalize driving rules across
North American and Australian jurisdictions, identifying possible restriction that an
adversary can exploit. Likewise, these rules can be used to test the adaptability of AVs
to new contexts and to establish a formal basis for context-aware AV testing. Next,
we apply optimization-based adversarial search to both ACC-controlled vehicle pla-
toons and obstacle-avoiding drone swarms. We uncover maneuvers that an adversary
can use against the system that range from crash-inducing patterns against platooning
controllers to herding strategies that divert swarms from their objectives. Finally, to
address the gap regarding the possible solutions to an adversarial attack we explore how
a drone can recover from it by using LVLMs to understand its context and select a safe
landing surface.

Event Host: Diego Ortiz Barbosa, Ph.D. Candidate, Computer Science & Engineering 

Advisor: Alvaro A Cardenas