Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

TL;DR

This survey reviews recent advances in adversarial attacks and defenses on 3D point cloud classification, highlighting vulnerabilities and summarizing current strategies to improve robustness in deep learning models.

Contribution

It provides a comprehensive overview of attack and defense techniques in 3D point cloud classification, aiding future research in this emerging area.

Findings

Summarizes recent adversarial attack methods on point clouds.

Reviews defense strategies including data and model-focused approaches.

Identifies challenges and future directions in the field.

Abstract

Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds is becoming increasingly popular for addressing various tasks in this field. Despite remarkable achievements, deep learning algorithms are vulnerable to adversarial attacks. These attacks are imperceptible to the human eye but can easily fool deep neural networks in the testing and deployment stage. To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point cloud classification.This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years. Additionally, it provides an overview of defense strategies, organized into data-focused and model-focused methods. Finally, it presents several current challenges and potential future research directions in this domain.