CVDec 22, 2025

6DAttack: Backdoor Attacks in the 6DoF Pose Estimation

arXiv:2512.19058v12 citationsh-index: 5
Originality Highly original
AI Analysis

This reveals a serious, underexplored security threat to robotics, AR/VR, and autonomous systems.

The paper tackles the problem of backdoor attacks in 6DoF pose estimation, proposing 6DAttack, which achieves up to 100% attack success rate and 97.70% ADD-P accuracy on triggered samples without compromising clean performance.

Deep learning advances have enabled accurate six-degree-of-freedom (6DoF) object pose estimation, widely used in robotics, AR/VR, and autonomous systems. However, backdoor attacks pose significant security risks. While most research focuses on 2D vision, 6DoF pose estimation remains largely unexplored. Unlike traditional backdoors that only change classes, 6DoF attacks must control continuous parameters like translation and rotation, rendering 2D methods inapplicable. We propose 6DAttack, a framework using 3D object triggers to induce controlled erroneous poses while maintaining normal behavior. Evaluations on PVNet, DenseFusion, and PoseDiffusion across LINEMOD, YCB-Video, and CO3D show high attack success rates (ASRs) without compromising clean performance. Backdoored models achieve up to 100% clean ADD accuracy and 100% ASR, with triggered samples reaching 97.70% ADD-P. Furthermore, a representative defense remains ineffective. Our findings reveal a serious, underexplored threat to 6DoF pose estimation.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes