Steganography for Neural Radiance Fields by Backdooring

TL;DR

This paper introduces a novel steganography method using Neural Radiance Fields (NeRF) to securely embed and extract messages via viewpoint synthesis, achieving high capacity and security against attackers.

Contribution

It presents a new model steganography scheme leveraging NeRF's viewpoint synthesis and overfitting-based message extraction, enhancing security and efficiency.

Findings

Achieves 100% message extraction accuracy.

Provides high-capacity steganography with fast performance.

Ensures security through extensive viewpoint key space.

Abstract

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.