Crash, Fail-safe, or Recover: Securing Robotic Autonomous Vehicles

Pritam Dash and Karthik Pattabiraman, University of British Columbia

This tutorial explores how physical sensor attacks compromise the safety and control of Robotic Autonomous Vehicles (RAVs), with a focus on state estimation failures. It will present and compare attack recovery techniques for both traditional PID-based and deep reinforcement learning (Deep-RL) controlled RAVs, including software sensors, feed-forward control, and multi-objective adversarial training. Through a mix of lectures and hands-on virtual activities, participants will learn to analyze attacks and apply resilient control strategies across different RAV architectures.

Pritam Dash is a Ph.D. student in Electrical and Computer Engineering at the University of British Columbia (UBC), Canada. Pritam's research focuses on the safety and security of autonomous systems. Specifically, analyzing vulnerabilities in sensing-perception modules, control systems, AI techniques, and mitigating them to ensure safety in autonomous systems. Pritam received master's degree in Electrical and Computer Engineering also from UBC. Before joining UBC, Pritam worked at IAIK, Graz University of Technology on projects related to identity management, privacy, and end-to-end confidentiality in cloud systems.
Connect: 
@_pritamdash

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@conference {309271,
author = {Pritam Dash and Karthik Pattabiraman},
title = {Crash, Fail-safe, or Recover: Securing Robotic Autonomous Vehicles},
year = {2025},
address = {Seattle, WA},
publisher = {USENIX Association},
month = aug
}
Download
PDF icon Dash Tutorial PDF
View the slides