Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey
This is an incremental survey paper that addresses the problem of adversarial security for researchers and practitioners working on 3D point cloud classification.
This survey paper examines the vulnerability of deep learning algorithms for 3D point cloud classification to adversarial attacks, which are imperceptible to humans but can fool neural networks, and it summarizes current attack generation methods and defense strategies while identifying challenges and future directions.
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.