# Learning-Based Reconstruction Attacks on Coordinate-Obfuscated Point Clouds

arXiv: https://arxiv.org/abs/2609.02568 · HTML: https://mlsanity.com/paper/2609.02568/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review](https://mlsanity.com/paper/2005.09830/) (2020)
- [Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification](https://mlsanity.com/paper/2004.01301/) (2020)
- [Securing Immersive 360 Video Streams through Attribute-Based Selective Encryption](https://mlsanity.com/paper/2505.04466/) (2025)
- [Secure AI-Driven Super-Resolution for Real-Time Mixed Reality Applications](https://mlsanity.com/paper/2512.15823/) (2025)
- [ABE-VVS: Attribute-Based Encrypted Volumetric Video Streaming](https://mlsanity.com/paper/2601.08987/) (2026)

## Abstract (arXiv)

Volumetric video based on point cloud representations enables immersive virtual and augmented reality applications but introduces significant challenges for efficient and secure content delivery. Prior work proposed a selective coordinate encryption framework for point clouds that encrypts only a subset of coordinates, reducing computational costs while visually degrading unauthorized content. However, it remains unclear whether the remaining unencrypted information is sufficient to enable content reconstruction. In this paper, we evaluate the robustness of selective coordinate encryption against machine learning-based reconstruction attacks. We consider an attacker with access to selectively encrypted point clouds attempting to recover encrypted coordinates without decryption by exploiting spatial and geometric correlations in the unencrypted data. We evaluate PointNet and Random Forest models under two encryption granularities: textttX, where all X coordinates are encrypted, and texttt2X, where every second X coordinate is encrypted. Our results show that reconstructing fully encrypted X coordinates remains challenging, whereas the texttt2X scheme leaks sufficient information through neighboring coordinates to enable accurate reconstruction. These findings demonstrate that the security of selective coordinate encryption depends strongly on encryption granularity.