# Multimodal Robust Prompt Distillation for 3D Point Cloud Models

arXiv: https://arxiv.org/abs/2511.21574 · HTML: https://mlsanity.com/paper/2511.21574/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training](https://mlsanity.com/paper/2210.01055/) (2022)
- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers](https://mlsanity.com/paper/1901.03006/) (2019)
- [AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds](https://mlsanity.com/paper/1912.00461/) (2019)
- [Adversarial Objects Against LiDAR-Based Autonomous Driving Systems](https://mlsanity.com/paper/1907.05418/) (2019)
- [Robustness of 3D Deep Learning in an Adversarial Setting](https://mlsanity.com/paper/1904.00923/) (2019)
- [On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attacks](https://mlsanity.com/paper/2002.12222/) (2020)
- [IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration](https://mlsanity.com/paper/2010.05272/) (2020)
- [3D Adversarial Attacks Beyond Point Cloud](https://mlsanity.com/paper/2104.12146/) (2021)
- [Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey](https://mlsanity.com/paper/2407.17877/) (2024)
- [Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion](https://mlsanity.com/paper/2211.16247/) (2022)

## Abstract (arXiv)

Adversarial attacks pose a significant threat to learning-based 3D point cloud models, critically undermining their reliability in security-sensitive applications. Existing defense methods often suffer from (1) high computational overhead and (2) poor generalization ability across diverse attack types. To bridge these gaps, we propose a novel yet efficient teacher-student framework, namely Multimodal Robust Prompt Distillation (MRPD) for distilling robust 3D point cloud model. It learns lightweight prompts by aligning student point cloud model's features with robust embeddings from three distinct teachers: a vision model processing depth projections, a high-performance 3D model, and a text encoder. To ensure a reliable knowledge transfer, this distillation is guided by a confidence-gated mechanism which dynamically balances the contribution of all input modalities. Notably, since the distillation is all during the training stage, there is no additional computational cost at inference. Extensive experiments demonstrate that MRPD substantially outperforms state-of-the-art defense methods against a wide range of white-box and black-box attacks, while even achieving better performance on clean data. Our work presents a new, practical paradigm for building robust 3D vision systems by efficiently harnessing multimodal knowledge.