Multitask Identity-Aware Image Steganography via Minimax Optimization

TL;DR

This paper introduces MIAIS, a multitask framework for high-capacity image steganography that preserves identity information for direct recognition and optionally restores secret images, enhancing security and flexibility.

Contribution

The paper proposes a novel multitask identity-aware steganography framework using minimax optimization to simultaneously hide identity info and optionally restore secret images.

Findings

Effective identity preservation in container images.

Robustness transfer across different datasets.

Outperforms existing steganography methods.

Abstract

High-capacity image steganography, aimed at concealing a secret image in a cover image, is a technique to preserve sensitive data, e.g., faces and fingerprints. Previous methods focus on the security during transmission and subsequently run a risk of privacy leakage after the restoration of secret images at the receiving end. To address this issue, we propose a framework, called Multitask Identity-Aware Image Steganography (MIAIS), to achieve direct recognition on container images without restoring secret images. The key issue of the direct recognition is to preserve identity information of secret images into container images and make container images look similar to cover images at the same time. Thus, we introduce a simple content loss to preserve the identity information, and design a minimax optimization to deal with the contradictory aspects. We demonstrate that the robustness results can be transferred across different cover datasets. In order to be flexible for the secret image restoration in some cases, we incorporate an optional restoration network into our method, providing a multitask framework. The experiments under the multitask scenario show the effectiveness of our framework compared with other visual information hiding methods and state-of-the-art high-capacity image steganography methods.