# Gaussian Splatting Under Attack: Investigating Adversarial Noise in 3D Objects

arXiv: https://arxiv.org/abs/2412.02803 · HTML: https://mlsanity.com/paper/2412.02803/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Builds on (most cited first, 5 of 5)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Vision Language Models in Autonomous Driving: A Survey and Outlook](https://mlsanity.com/paper/2310.14414/) (2023)
- [Vision-Language Intelligence: Tasks, Representation Learning, and Large Models](https://mlsanity.com/paper/2203.01922/) (2022)

## Built on by (most cited first, 11 of 11)

- [GaussTrap: Stealthy Poisoning Attacks on 3D Gaussian Splatting for Targeted Scene Confusion](https://mlsanity.com/paper/2504.20829/) (2025)
- [StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions](https://mlsanity.com/paper/2510.02314/) (2025)
- [Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting](https://mlsanity.com/paper/2603.12796/) (2026)
- [PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems](https://mlsanity.com/paper/2604.16540/) (2026)
- [3D Gaussian Splat Vulnerabilities](https://mlsanity.com/paper/2506.00280/) (2025)
- [ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages](https://mlsanity.com/paper/2508.11854/) (2025)
- [BiTAA: A Bi-Task Adversarial Attack for Object Detection and Depth Estimation via 3D Gaussian Splatting](https://mlsanity.com/paper/2509.19793/) (2025)
- [DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering](https://mlsanity.com/paper/2602.19323/) (2026)
- [AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models](https://mlsanity.com/paper/2603.23686/) (2026)
- [PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction](https://mlsanity.com/paper/2604.13153/) (2026)
- [3D FaceShell: Attribute Transfer in 3D Face Avatars as a VLM Defense Mechanism](https://mlsanity.com/paper/2607.16280/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting has advanced radiance field reconstruction, enabling high-quality view synthesis and fast rendering in 3D modeling. While adversarial attacks on object detection models are well-studied for 2D images, their impact on 3D models remains underexplored. This work introduces the Masked Iterative Fast Gradient Sign Method (M-IFGSM), designed to generate adversarial noise targeting the CLIP vision-language model. M-IFGSM specifically alters the object of interest by focusing perturbations on masked regions, degrading the performance of CLIP's zero-shot object detection capability when applied to 3D models. Using eight objects from the Common Objects 3D (CO3D) dataset, we demonstrate that our method effectively reduces the accuracy and confidence of the model, with adversarial noise being nearly imperceptible to human observers. The top-1 accuracy in original model renders drops from 95.4% to 12.5% for train images and from 91.2% to 35.4% for test images, with confidence levels reflecting this shift from true classification to misclassification, underscoring the risks of adversarial attacks on 3D models in applications such as autonomous driving, robotics, and surveillance. The significance of this research lies in its potential to expose vulnerabilities in modern 3D vision models, including radiance fields, prompting the development of more robust defenses and security measures in critical real-world applications.