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

PrivacyFlash Pro: Automating Privacy Policy Generation for Mobile Apps

Sebastian Zimmeck (Wesleyan University), Rafael Goldstein (Wesleyan University), David Baraka (Wesleyan University)

Read More

A Formal Analysis of the FIDO UAF Protocol

Haonan Feng (Beijing University of Posts and Telecommunications), Hui Li (Beijing University of Posts and Telecommunications), Xuesong Pan (Beijing University of Posts and Telecommunications), Ziming Zhao (University at Buffalo)

Read More

Demo #9: Attacking Multi-Sensor Fusion based Localization in High-Level...

Junjie Shen, Jun Yeon Won, Zeyuan Chen and Qi Alfred Chen (UC Irvine)

Read More