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

PHOENIX: Device-Centric Cellular Network Protocol Monitoring using Runtime Verification

Mitziu Echeverria (The University of Iowa), Zeeshan Ahmed (The University of Iowa), Bincheng Wang (The University of Iowa), M. Fareed Arif (The University of Iowa), Syed Rafiul Hussain (Pennsylvania State University), Omar Chowdhury (The University of Iowa)

Read More

Tales of Favicons and Caches: Persistent Tracking in Modern...

Konstantinos Solomos (University of Illinois at Chicago), John Kristoff (University of Illinois at Chicago), Chris Kanich (University of Illinois at Chicago), Jason Polakis (University of Illinois at Chicago)

Read More

MUVIDS: False MAVLink Injection Attack Detection in Communication for...

Seonghoon Jeong, Eunji Park, Kang Uk Seo, Jeong Do Yoo, and Huy Kang Kim (Korea University)

Read More

Differential Training: A Generic Framework to Reduce Label Noises...

Jiayun Xu (Singapore Management University), Yingjiu Li (University of Oregon), Robert H. Deng (Singapore Management University)

Read More