Compressive imaging for thwarting adversarial attacks on 3D point cloud classifiers

Vladislav Kravets, Bahram Javidi, Adrian Stern

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Three dimensional (3D) point cloud classifiers are used extensively in safety crucial applications such as autonomous cars, face recognition, military applications, and many more. Despite the critical importance of their reliability, 3D classifiers are prone to adversarial attacks that can be crafted in the real world. While it is possible to use known methods to prevent adversarial attacks, they can be easily counter-attacked, leading to an arms race between the attacker and the defender. Here, we propose to use 3D compressive sensing to recover an original label of the 3D object. Since compressive sensing inherently encodes the 3D signal, it also prevents the arms race between the attacker and the defender. The 3D compressive sensing we consider is a single pixel camera (SPC) system that can be implemented in Light Detection and Ranging (LiDAR) systems.

Original languageEnglish
Pages (from-to)42726-42737
Number of pages12
JournalOptics Express
Volume29
Issue number26
DOIs
StatePublished - 20 Dec 2021

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Fingerprint

Dive into the research topics of 'Compressive imaging for thwarting adversarial attacks on 3D point cloud classifiers'. Together they form a unique fingerprint.

Cite this