Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspective
This addresses the problem of limited generalization in adversarial attacks for point cloud models, offering a more robust solution for security applications, though it is incremental in improving transferability.
The paper tackled the challenge of transferable adversarial attacks on point clouds by proposing CoSA, a framework that operates in a low-dimensional semantic space, resulting in consistent outperformance of state-of-the-art methods across multiple datasets and architectures.
Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen architectures. In this paper, we rethink adversarial transferability from a compact subspace perspective and propose CoSA, a transferable attack framework that operates within a shared low-dimensional semantic space. Specifically, each point cloud is represented as a compact combination of class-specific prototypes that capture shared semantic structure, while adversarial perturbations are optimized within a low-rank subspace to induce coherent and architecture-agnostic variations. This design suppresses model-dependent noise and constrains perturbations to semantically meaningful directions, thereby improving cross-model transferability without relying on surrogate-specific artifacts. Extensive experiments on multiple datasets and network architectures demonstrate that CoSA consistently outperforms state-of-the-art transferable attacks, while maintaining competitive imperceptibility and robustness under common defense strategies. Codes will be made public upon paper acceptance.