🤖 AI Summary
Existing deep learning-based steganography methods require auxiliary training of a separate message extractor, raising suspicion among steganalysts and limiting practical deployment. To address this, we propose StegaINR—the first framework to introduce Implicit Neural Representations (INRs) into steganography. StegaINR encodes secret messages as parameters of a continuous function and directly embeds them into the carrier function itself, enabling the carrier to serve simultaneously as both cover and decoder. Message recovery is lossless and requires only a shared secret key, eliminating the need for an independent extractor. This achieves function-level information hiding, offering high undetectability, cross-modal generality (validated on images and climate data), and support for diverse message types—including text and binary data. Experimental results demonstrate a significant reduction in detection rates by mainstream steganalyzers.
📝 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.
