MOBA: A Material-Oriented Backdoor Attack against LiDAR-based 3D Object Detection Systems
Saket S. Chaturvedi, Gaurav Bagwe, Lan Zhang, Pan He, Xiaoyong Yuan

TL;DR
This paper introduces MOBA, a novel backdoor attack framework for LiDAR-based 3D object detection that uses material properties to create physically realizable triggers, significantly improving attack success rates.
Contribution
MOBA explicitly models material properties to bridge the digital-physical gap, enabling effective and robust physical backdoor triggers for LiDAR systems.
Findings
Achieves 93.50% attack success rate, outperforming prior methods by over 41%.
Identifies titanium dioxide as an effective trigger material due to its reflectivity and resilience.
Develops a simulation pipeline that accurately mimics physical trigger behavior in digital models.
Abstract
LiDAR-based 3D object detection is widely used in safety-critical systems. However, these systems remain vulnerable to backdoor attacks that embed hidden malicious behaviors during training. A key limitation of existing backdoor attacks is their lack of physical realizability, primarily due to the digital-to-physical domain gap. Digital triggers often fail in real-world settings because they overlook material-dependent LiDAR reflection properties. On the other hand, physically constructed triggers are often unoptimized, leading to low effectiveness or easy detectability.This paper introduces Material-Oriented Backdoor Attack (MOBA), a novel framework that bridges the digital-physical gap by explicitly modeling the material properties of real-world triggers. MOBA tackles two key challenges in physical backdoor design: 1) robustness of the trigger material under diverse environmental…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Advanced Neural Network Applications · Physical Unclonable Functions (PUFs) and Hardware Security
