# Steganography for Neural Radiance Fields by Backdooring

arXiv: https://arxiv.org/abs/2309.10503 · HTML: https://mlsanity.com/paper/2309.10503/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2023.

## Built on by (most cited first, 3 of 3)

- [IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields](https://mlsanity.com/paper/2407.11921/) (2024)
- [Event Trojan: Asynchronous Event-based Backdoor Attacks](https://mlsanity.com/paper/2407.06838/) (2024)
- [StegoNGP: 3D Cryptographic Steganography using Instant-NGP](https://mlsanity.com/paper/2603.00949/) (2026)

## Abstract (arXiv)

The utilization of implicit representation for visual data (such as images, videos, and 3D models) has recently gained significant attention in computer vision research. In this letter, we propose a novel model steganography scheme with implicit neural representation. The message sender leverages Neural Radiance Fields (NeRF) and its viewpoint synthesis capabilities by introducing a viewpoint as a key. The NeRF model generates a secret viewpoint image, which serves as a backdoor. Subsequently, we train a message extractor using overfitting to establish a one-to-one mapping between the secret message and the secret viewpoint image. The sender delivers the trained NeRF model and the message extractor to the receiver over the open channel, and the receiver utilizes the key shared by both parties to obtain the rendered image in the secret view from the NeRF model, and then obtains the secret message through the message extractor. The inherent complexity of the viewpoint information prevents attackers from stealing the secret message accurately. Experimental results demonstrate that the message extractor trained in this letter achieves high-capacity steganography with fast performance, achieving a 100% accuracy in message extraction. Furthermore, the extensive viewpoint key space of NeRF ensures the security of the steganography scheme.