Congratulations to both Dr. Rampazzi and her Ph.D student Sri Hrushikesh Varma Bhupathiraju for wining two awards for their work-in-progress (WIP) paper, titled: “WIP: Infrared Laser Reflection Attack Against Traffic Sign Recognition Systems”. These awards include: The ETAS best short/WIP Paper award and the Qualcomm Best Demo Award at the Inaugural Symposium on Vehicle Security and Privacy at San Diego Feb 27th 2023. The symposium was co-located with NDSS (Network and Distributed System Security (NDSS) Symposium).
Dr. Rampazzi states:
“In this work in progress, we present our preliminary results and the discovery of a new vulnerability in cameras that can undermine autonomous vehicle traffic signs recognition systems. We show that adversaries can use this vulnerability to create invisible (to a human) adversarial shapes on the target sign that induces traffic sign misclassification (e.g., speed limit sign perceived as a stop sign).
We demonstrate this on controlled closed setting and in simulations. Next, we plan to investigate the attacker capabilities in real-world autonomous driving scenarios in a variety of environmental conditions and elaborate a defense strategy to mitigate the threat. This research is part of my lab’s ongoing effort to investigate the security and safety of autonomous vehicles against physical attacks on sensors.”
The research was led by Ph.D. student Sri Hrushikesh Varma Bhupathiraju, and collaboration with UCI Irvine PhD student Takami Sato. This is a joint work between CPSec lab), UCI Irvine, The University of Electro-Communications (Tokyo, Japan), and Toyota InfoTech Labs.
The project was funded by NSF funding, and unrestricted research funds from Toyota InfoTech Labs.
Further Information on the research can be found here