# 6DAttack: Backdoor Attacks in the 6DoF Pose Estimation

arXiv: https://arxiv.org/abs/2512.19058 · HTML: https://mlsanity.com/paper/2512.19058/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 22 Dec 2025.

## Builds on (most cited first, 21 of 21)

- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [A backdoor attack against LSTM-based text classification systems](https://mlsanity.com/paper/1905.12457/) (2019)
- [BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects](https://mlsanity.com/paper/2303.14158/) (2023)
- [PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment](https://mlsanity.com/paper/2306.15667/) (2023)
- [ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape](https://mlsanity.com/paper/1812.02781/) (2018)
- [Is feature selection secure against training data poisoning?](https://mlsanity.com/paper/1804.07933/) (2018)
- [Backdoor Attack in the Physical World](https://mlsanity.com/paper/2104.02361/) (2021)
- [BadDet: Backdoor Attacks on Object Detection](https://mlsanity.com/paper/2205.14497/) (2022)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [Fine-Tuning Is All You Need to Mitigate Backdoor Attacks](https://mlsanity.com/paper/2212.09067/) (2022)
- [Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview](https://mlsanity.com/paper/2105.14291/) (2021)
- [Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving](https://mlsanity.com/paper/2203.00858/) (2022)
- [Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation](https://mlsanity.com/paper/2506.07214/) (2025)
- [Influencer Backdoor Attack on Semantic Segmentation](https://mlsanity.com/paper/2303.12054/) (2023)
- [Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach](https://mlsanity.com/paper/2508.15778/) (2025)

## Built on by (most cited first, 1 of 1)

- [Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models](https://mlsanity.com/paper/2512.22046/) (2025)

## Abstract (arXiv)

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.