Bo Yang (Zhejiang University), Yushi Cheng (Tsinghua University), Zizhi Jin (Zhejiang University), Xiaoyu Ji (Zhejiang University) and Wenyuan Xu (Zhejiang University)

Due to the booming of autonomous driving, in which LiDAR plays a critical role in the task of environment perception, its reliability issues have drawn much attention recently. LiDARs usually utilize deep neural models for 3D point cloud perception, which have been demonstrated to be vulnerable to imperceptible adversarial examples. However, prior work usually manipulates point clouds in the digital world without considering the physical working principle of the actual LiDAR. As a result, the generated adversarial point clouds may be realizable and effective in simulation but cannot be perceived by physical LiDARs. In this work, we introduce the physical principle of LiDARs and propose a new method for generating 3D adversarial point clouds in accord with it that can achieve two types of spoofing attacks: object hiding and object creating. We also evaluate the effectiveness of the proposed method with two 3D object detectors on the KITTI vision benchmark.

View More Papers

Model-Agnostic Defense for Lane Detection against Adversarial Attack

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

Read More

Detecting Obfuscated Function Clones in Binaries using Machine Learning

Michael Pucher (University of Vienna), Christian Kudera (SBA Research), Georg Merzdovnik (SBA Research)

Read More

Demo #6: Impact of Stealthy Attacks on Autonomous Robotic...

Pritam Dash, Mehdi Karimibiuki, and Karthik Pattabiraman (University of British Columbia)

Read More