Unified Steganography via Implicit Neural Representation

TL;DR

U-INR introduces a universal steganography method using Implicit Neural Representation, enabling secret data embedding across various data types without designing specific frameworks for each, thus enhancing generalizability and security.

Contribution

The paper proposes U-INR, a novel INR-based steganography technique that embeds secret data directly into neural network neurons, using a key-based strategy for data positioning across multiple data formats.

Findings

Effective across images, videos, audio, SDF, and NeRF data types.

Demonstrates improved generalizability and security in steganography.

Outperforms traditional methods in embedding capacity and robustness.

Abstract

Digital steganography is the practice of concealing for encrypted data transmission. Typically, steganography methods embed secret data into cover data to create stega data that incorporates hidden secret data. However, steganography techniques often require designing specific frameworks for each data type, which restricts their generalizability. In this paper, we present U-INR, a novel method for steganography via Implicit Neural Representation (INR). Rather than using the specific framework for each data format, we directly use the neurons of the INR network to represent the secret data and cover data across different data types. To achieve this idea, a private key is shared between the data sender and receivers. Such a private key can be used to determine the position of secret data in INR networks. To effectively leverage this key, we further introduce a key-based selection strategy that can be used to determine the position within the INRs for data storage. Comprehensive experiments across multiple data types, including images, videos, audio, and SDF and NeRF, demonstrate the generalizability and effectiveness of U-INR, emphasizing its potential for improving data security and privacy in various applications.