Hiding Functions within Functions: Steganography by Implicit Neural Representations

TL;DR

This paper introduces StegaINR, a novel steganography method using Implicit Neural Representations to embed secret functions into stego functions, enabling secure message transmission without additional extractors.

Contribution

First to incorporate INR into steganography, allowing embedding of functions as messages and simplifying secure communication with shared keys.

Findings

Effective on image and climate data

Handles various message types

First use of INR in steganography

Abstract

Deep steganography utilizes the powerful capabilities of deep neural networks to embed and extract messages, but its reliance on an additional message extractor limits its practical use due to the added suspicion it can raise from steganalyzers. To address this problem, we propose StegaINR, which utilizes Implicit Neural Representation (INR) to implement steganography. StegaINR embeds a secret function into a stego function, which serves as both the message extractor and the stego media for secure transmission on a public channel. Recipients need only use a shared key to recover the secret function from the stego function, allowing them to obtain the secret message. Our approach makes use of continuous functions, enabling it to handle various types of messages. To our knowledge, this is the first work to introduce INR into steganography. We performed evaluations on image and climate data to test our method in different deployment contexts.