Ed of Charles Sturt University

Autonomous robots are increasingly deployed across defence, industrial, and public-sector settings, yet remain exposed to cyber-physical attacks that conventional cybersecurity handles poorly. Standard methods treat a robot as a generic computing endpoint, ignoring the physical constraints that set it apart. The consequence is that a network breach quickly becomes physical harm through compromised navigation, manipulated sensor streams, or hijacked actuators.

This talk presents a physics-informed approach to securing robotic vehicles, built on a simple premise: robots obey physics, and their kinematic and electromechanical constraints leave detectable signatures usable for intrusion detection. The first part develops detectors that operate within these constraints across several platforms, including deep-learning detection of denial-of-service attacks on ROS 2 ground vehicles, power-consumption side channels for man-in-the-middle attacks on differential-drive robots, and bio-mechanical coupling between wing oscillation and inertial measurements on flapping-wing micro air vehicles. These methods achieve high detection performance while remaining light enough for microcontroller and single-board deployment.

The second part outlines the direction for the remaining programme: assessing how resilient physics-informed detectors are to adversarial evasion crafted within physical constraints, and developing defences that harden them against adaptive adversaries. The talk closes with the open questions and benchmarks needed to move from detection toward trustworthy, attack-resilient autonomy.

Biography:

Eduardo Fraga da Silva earned his Master's degree in Cloud Computing from Charles Sturt University (Bathurst, NSW, Australia). He is currently a PhD candidate at the Artificial Intelligence and Cyber Futures (AICF) Institute, Charles Sturt University, in the second year of his candidature. His research sits at the intersection of robotics, cybersecurity, and machine learning, with a focus on improving the security and operational resilience of autonomous robotic systems. In particular, he investigates cyber-physical attack detection for mobile robots by combining data-driven methods with system and physics-aware signals that reflect the underlying dynamics of the platform. Before his doctoral studies, he spent five years as a data scientist delivering applied machine learning and deployment-oriented analytics across time-series, computer-vision, and natural-language problems. His broader interests include deep learning for time-series sensing, robust feature engineering for resource-constrained robots, and evaluation protocols that test generalisation to realistic and unseen attack behaviours.

Dr. Fendy Santoso (Ed's PhD supervisor) received the master’s degree in electrical and computer Systems Engineering from Monash University, Melbourne, VIC, Australia, in 2007, and the Ph.D. degree in Electrical Engineering from The University of New South Wales (UNSW), Sydney, NSW, Australia, in 2012. He is currently the Cyber-Physical Systems Lead with the Artificial Intelligence and Cyber Futures (AICF) Institute, Charles Sturt University, Canberra ACT, where he leads research initiatives in intelligent cyber-physical systems, robotics, trusted autonomy, AI-enabled systems, and cybersecurity.  He also holds a Visiting Research Fellowship with the Autonomous Systems Laboratory, UNSW Canberra, ACT, Australia. Currently, he is a Chief Investigator (CI) of the CSIRO Next Generation Graduates Program and two successful ARC Linkage Projects in robotics, AI-enabled autonomy, and cybersecurity, working closely with industry on trusted and resilient autonomous systems. His research sits at the intersection of robotics, artificial intelligence, and cybersecurity, focusing on trusted and resilient autonomous systems operating in real-world adversarial environments. His work has also contributed to bio-mimetic self-learning robotic systems based on evolving type-2 fuzzy intelligence frameworks. He was the recipient of the Distinguished Early Career Travel Fellowship under the Vice-Chancellor’s Fellowship scheme at the University of Wollongong, Wollongong, NSW, Australia.

Email:

Address:Canberra, Australia