STONE: Pioneering the One-to-N Universal Backdoor Threat in 3D Point Cloud

TL;DR

This paper introduces STONE, a novel method for one-to-N backdoor attacks on 3D point cloud models, using a spherical trigger design and theoretical NTK analysis, achieving high success rates without affecting clean data accuracy.

Contribution

It pioneers the first practical and theoretical framework for multi-target backdoor attacks in 3D point cloud models, expanding the threat landscape.

Findings

Achieves up to 100% attack success rate

Maintains high clean-data accuracy

Establishes a theoretical foundation with NTK analysis

Abstract

Backdoor attacks pose a critical threat to deep learning, especially in safety-sensitive 3D domains such as autonomous driving and robotics. While potent, existing attacks on 3D point clouds are predominantly limited to one-to-one paradigms. The more flexible and universal one-to-N multi-target backdoor threat remains largely unexplored, lacking both theoretical and practical foundations. To bridge this gap, we propose STONE (Spherical Trigger One-to-N universal backdoor Enabling), the first method to instantiate this threat via a configurable spherical trigger design. Its parameterized spatial properties establish a dynamic key space, enabling a single trigger to map to multiple target labels. Theoretically, we ground STONE in a Neural Tangent Kernel (NTK) analysis, providing the first formal basis for one-to-N mappings in 3D models. Empirically, extensive evaluations demonstrate high attack success rates (up to 100\%) without compromising clean-data accuracy. This work establishes a foundational benchmark for multi-target backdoor threats under dirty-label and black-box settings in 3D vision -- a crucial step toward securing future intelligent systems.