Demo: Security of Deep Learning based Automated Lane Centering under Physical-World Attack

Takami Sato, Junjie Shen, Ningfei Wang, Yunhan Jack Jia, Xue Lin, Qi Alfred Chen

Abstract: Automatic Lane Centering (ALC) systems are convenient and widely deployed today, but they are also highly security and safety critical. Recent research shows that Dirty Road Patch (DRP) attack can successfully attack DNN-based ALC systems. In this work, we will demonstrate the DRP attack on a production-level simulator and a physical-world setup.