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

Preventing Kernel Hacks with HAKCs

Derrick McKee (Purdue University), Yianni Giannaris (MIT CSAIL), Carolina Ortega (MIT CSAIL), Howard Shrobe (MIT CSAIL), Mathias Payer (EPFL), Hamed Okhravi (MIT Lincoln Laboratory), Nathan Burow (MIT Lincoln Laboratory)

Read More

Property Inference Attacks Against GANs

Junhao Zhou (Xi'an Jiaotong University), Yufei Chen (Xi'an Jiaotong University), Chao Shen (Xi'an Jiaotong University), Yang Zhang (CISPA Helmholtz Center for Information Security)

Read More

WIP: Interrupt Attack on TEE-protected Robotic Vehicles

Mulong Luo (Cornell University) and G. Edward Suh (Cornell University)

Read More

EqualNet: A Secure and Practical Defense for Long-term Network...

Jinwoo Kim (KAIST), Eduard Marin (Telefonica Research (Spain)), Mauro Conti (University of Padua), Seungwon Shin (KAIST)

Read More