Henry Xu, An Ju, and David Wagner (UC Berkeley) Baidu Security Auto-Driving Security Award Winner ($1000 cash prize)!

Susceptibility of neural networks to adversarial attack prompts serious safety concerns for lane detection efforts, a domain where such models have been widely applied. Recent work on adversarial road patches have successfully induced perception of lane lines with arbitrary form, presenting an avenue for rogue control of vehicle behavior. In this paper, we propose a modular lane verification system that can catch such threats before the autonomous driving system is misled while remaining agnostic to the particular lane detection model. Our experiments show that implementing the system with a simple convolutional neural network (CNN) can defend against a wide gamut of attacks on lane detection models. With a 10% impact to inference time, we can detect 96% of bounded non-adaptive attacks, 90% of bounded adaptive attacks, and 98% of patch attacks while preserving accurate identification at least 95% of true lanes, indicating that our proposed verification system is effective at mitigating lane detection security risks with minimal overhead.

View More Papers

Physical Layer Data Manipulation Attacks on the CAN Bus

Abdullah Zubair Mohammed (Virginia Tech), Yanmao Man (University of Arizona), Ryan Gerdes (Virginia Tech), Ming Li (University of Arizona) and Z. Berkay Celik (Purdue University)

Read More

Comparative Analysis of the DoT with HTTPS Certificate Ecosystems

Ali Sadeghi Jahromi, AbdelRahman Abdou (Carleton University)

Read More

PGFUZZ: Policy-Guided Fuzzing for Robotic Vehicles

Hyungsub Kim (Purdue University), Muslum Ozgur Ozmen (Purdue University), Antonio Bianchi (Purdue University), Z. Berkay Celik (Purdue University), Dongyan Xu (Purdue University)

Read More