# Steganography of Steganographic Networks

## TL;DR

This paper introduces a novel method for covertly transmitting steganographic neural networks by disguising them as ordinary models, enabling secure communication of large DNNs in public channels.

## Contribution

It proposes a new scheme to hide steganographic networks within normal DNN models by selective filter tuning and partial optimization, enhancing covert communication capabilities.

## Key findings

- Effective concealment of steganographic networks demonstrated
- Preservation of secret task performance in disguised models
- Enhanced security for transmitting large neural networks

## Abstract

Steganography is a technique for covert communication between two parties. With the rapid development of deep neural networks (DNN), more and more steganographic networks are proposed recently, which are shown to be promising to achieve good performance. Unlike the traditional handcrafted steganographic tools, a steganographic network is relatively large in size. It raises concerns on how to covertly transmit the steganographic network in public channels, which is a crucial stage in the pipeline of steganography in real world applications. To address such an issue, we propose a novel scheme for steganography of steganographic networks in this paper. Unlike the existing steganographic schemes which focus on the subtle modification of the cover data to accommodate the secrets. We propose to disguise a steganographic network (termed as the secret DNN model) into a stego DNN model which performs an ordinary machine learning task (termed as the stego task). During the model disguising, we select and tune a subset of filters in the secret DNN model to preserve its function on the secret task, where the remaining filters are reactivated according to a partial optimization strategy to disguise the whole secret DNN model into a stego DNN model. The secret DNN model can be recovered from the stego DNN model when needed. Various experiments have been conducted to demonstrate the advantage of our proposed method for covert communication of steganographic networks as well as general DNN models.