In autonomous driving (AD) vehicles, Multi-Sensor Fusion (MSF) is used to combine perception results from multiple sensors such as LiDARs (Light Detection And Ranging) and cameras for both accuracy and robustness. In this work, we design the first attack that fundamentally defeats MSF-based AD perception by generating 3D adversarial objects. This demonstration will include video and figure demonstrations for the generated 3D adversarial objects and the end-to-end consequences.
Demo #1: Security of Multi-Sensor Fusion based Perception in AD under Physical-World Attacks
Yulong Cao (University of Michigan), Ningfei Wang (UC, Irvine), Chaowei Xiao (Arizona State University), Dawei Yang (University of Michigan), Jin Fang (Baidu Research), Ruigang Yang (University of Michigan), Qi Alfred Chen (UC, Irvine), Mingyan Liu (University of Michigan) and Bo Li (University of Illinois at Urbana-Champaign)
View More Papers
PHYjacking: Physical Input Hijacking for Zero-Permission Authorization Attacks on...
Xianbo Wang (The Chinese University of Hong Kong), Shangcheng Shi (The Chinese University of Hong Kong), Yikang Chen (The Chinese...
Read MoreEvaluating Euler: Experimental Results of Network Anomaly Detection Models
Isaiah J. King (The George Washington University)
Read MoreChhoyhopper: A Moving Target Defense with IPv6
A S M Rizvi (University of Southern California/Information Sciences Institute) and John Heidemann (University of Southern California/Information Sciences Institute)
Read More